阅读说明：本技术 语音识别方法、装置、电子设备和存储介质 (Voice recognition method and device, electronic equipment and storage medium ) 是由 彭经伟 陈真 于 2021-08-23 设计创作，主要内容包括：本公开提供了一种语音识别方法、装置、电子设备和存储介质,涉及人工智能技术领域,尤其涉及语音识别、尾点检测、自然语言处理技术领域。具体实现方案为：对语音信息进行语音识别；响应于从所述语音信息中识别到预设关键词,将尾点检测的等待时长由第一预设时长更新为第二预设时长,其中,所述第一预设时长小于所述第二预设时长。由此,可在语音信息中识别到预设关键词时,延长尾点检测的等待时长,从而可避免用户说出预设关键词之后的停顿导致识别出尾点的问题,还可避免语音识别过程由于识别出尾点而中断的问题,有助于延长语音识别时间,改善用户使用体验。(The present disclosure provides a speech recognition method, an apparatus, an electronic device and a storage medium, which relate to the technical field of artificial intelligence, and in particular to the technical field of speech recognition, tail point detection and natural language processing. The specific implementation scheme is as follows: carrying out voice recognition on the voice information; and in response to the recognition of a preset keyword from the voice information, updating the waiting time of the tail point detection from a first preset time to a second preset time, wherein the first preset time is less than the second preset time. Therefore, when the preset keyword is recognized in the voice information, the waiting time of tail point detection is prolonged, the problem that the tail point is recognized due to the fact that the user pauses after the preset keyword is spoken can be avoided, the problem that the voice recognition process is interrupted due to the fact that the tail point is recognized can be avoided, the voice recognition time is prolonged, and the user use experience is improved.)

1. A speech recognition method comprising:

carrying out voice recognition on the voice information;

and in response to the recognition of a preset keyword from the voice information, updating the waiting time of the tail point detection from a first preset time to a second preset time, wherein the first preset time is less than the second preset time.

2. The method of claim 1, wherein after updating the waiting duration of the tail-point detection from the first preset duration to the second preset duration, the method comprises:

and continuously carrying out tail point detection on the voice information according to the waiting time of the tail point detection to generate a tail point detection result.

3. The method of claim 2, wherein the continuing to perform tail point detection on the voice information according to the waiting duration of tail point detection to generate a tail point detection result comprises:

timing from the initial time of tail point detection to obtain the mute duration in the voice information;

recognizing that the mute duration is less than the waiting duration of the tail point detection, the voice information comprises voice, and the generated tail point detection result is that the tail point is not recognized; alternatively, the first and second electrodes may be,

and identifying that the mute duration reaches the waiting duration of the tail point detection, wherein the generated tail point detection result is the identified tail point.

4. The method of claim 3, wherein the method further comprises:

and updating the initial moment of the tail point detection based on the moment of recognizing the preset keyword from the voice information.

5. The method of claim 4, wherein updating the initial time of the tail point detection based on the time of the recognition of the preset keyword from the voice information comprises:

and taking the moment of recognizing the last recognition unit of the preset keyword from the voice information as the initial moment of detecting the tail point.

6. The method according to any one of claims 2-5, wherein the method further comprises:

responding to the tail point detection result that the tail point is not recognized, and controlling to continue voice recognition on the voice information; alternatively, the first and second electrodes may be,

and in response to the tail point detection result that the tail point is identified, controlling to stop carrying out voice identification on the voice information.

7. The method according to any one of claims 2-5, wherein the method further comprises:

and in response to the tail point detection result that the tail point is not identified, updating the waiting time length of the tail point detection from the second preset time length to the first preset time length.

8. A speech recognition apparatus comprising:

the recognition module is used for carrying out voice recognition on the voice information;

and the updating module is used for responding to the recognition of a preset keyword from the voice information and updating the waiting time length of the tail point detection from a first preset time length to a second preset time length, wherein the first preset time length is less than the second preset time length.

9. The apparatus of claim 8, wherein the apparatus further comprises: a detection module to:

and continuously carrying out tail point detection on the voice information according to the waiting time of the tail point detection to generate a tail point detection result.

10. The apparatus of claim 9, wherein the detection module is further configured to:

timing from the initial time of tail point detection to obtain the mute duration in the voice information;

recognizing that the mute duration is less than the waiting duration of the tail point detection, the voice information comprises voice, and the generated tail point detection result is that the tail point is not recognized; alternatively, the first and second electrodes may be,

and identifying that the mute duration reaches the waiting duration of the tail point detection, wherein the generated tail point detection result is the identified tail point.

11. The apparatus of claim 10, wherein the update module is further configured to:

and updating the initial moment of the tail point detection based on the moment of recognizing the preset keyword from the voice information.

12. The apparatus of claim 11, wherein the update module is further configured to:

and taking the moment of recognizing the last recognition unit of the preset keyword from the voice information as the initial moment of detecting the tail point.

13. The apparatus of any of claims 9-12, wherein the apparatus further comprises: a control module to:

responding to the tail point detection result that the tail point is not recognized, and controlling to continue voice recognition on the voice information; alternatively, the first and second electrodes may be,

and in response to the tail point detection result that the tail point is identified, controlling to stop carrying out voice identification on the voice information.

14. The apparatus of any of claims 9-12, wherein the update module is further configured to:

and in response to the tail point detection result that the tail point is not identified, updating the waiting time length of the tail point detection from the second preset time length to the first preset time length.

15. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the speech recognition method of any of claims 1-7.

16. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the speech recognition method according to any one of claims 1-7.

17. A computer program product comprising a computer program which, when being executed by a processor, carries out the steps of the speech recognition method according to any one of claims 1-7.

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a speech recognition method, apparatus, electronic device, storage medium, and computer program product.

Background

At present, with the development of technologies such as artificial intelligence and natural language processing, the voice recognition technology is widely applied in the fields of intelligent household appliances, robot voice interaction, vehicle-mounted voice and the like. For example, in a vehicle-mounted voice scene, the vehicle-mounted voice assistant can perform voice recognition on the speaking content of the vehicle-mounted personnel, acquire the user intention according to the voice recognition content and automatically execute a corresponding instruction, does not need manual operation of the user, is high in response speed and is favorable for driving safety. However, the voice recognition process in the related art is easily interrupted by the end point detection technology, and the obtained voice recognition result is incomplete, which affects the user experience.

Disclosure of Invention

The present disclosure provides a voice recognition method, apparatus, electronic device, storage medium, and computer program product.

According to an aspect of the present disclosure, there is provided a speech recognition method including: carrying out voice recognition on the voice information; and in response to the recognition of a preset keyword from the voice information, updating the waiting time of the tail point detection from a first preset time to a second preset time, wherein the first preset time is less than the second preset time.

According to another aspect of the present disclosure, there is provided a voice recognition apparatus including: the recognition module is used for carrying out voice recognition on the voice information; and the updating module is used for responding to the recognition of a preset keyword from the voice information and updating the waiting time length of the tail point detection from a first preset time length to a second preset time length, wherein the first preset time length is less than the second preset time length.

According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a speech recognition method.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform a speech recognition method.

According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when being executed by a processor, carries out the steps of the speech recognition method.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

fig. 1 is a schematic flow diagram of a speech recognition method according to a first embodiment of the present disclosure;

FIG. 2 is a flow chart diagram of a speech recognition method according to a second embodiment of the present disclosure;

FIG. 3 is a flow chart diagram of a speech recognition method according to a third embodiment of the present disclosure;

fig. 4 is a block diagram of a speech recognition apparatus according to a first embodiment of the present disclosure;

FIG. 5 is a block diagram of an electronic device for implementing a speech recognition method of an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

AI (Artificial Intelligence) is a technical science that studies and develops theories, methods, techniques and application systems for simulating, extending and expanding human Intelligence. At present, the AI technology has the advantages of high automation degree, high accuracy and low cost, and is widely applied.

Voice Recognition (Voice Recognition) is a technology for a machine to convert Voice signals into corresponding texts or commands through a Recognition and understanding process, and mainly comprises three aspects of a feature extraction technology, a pattern matching criterion and a model training technology.

NLU (Natural Language Processing) is a science for researching computer systems, especially software systems, which can effectively realize Natural Language communication, and is an important direction in the fields of computer science and artificial intelligence.

The end point Detection is a technology for identifying a Voice end point, namely, whether a user has spoken, is an important direction of a Voice Activity Detection (VAD) technology, and mainly comprises three aspects of audio framing, feature extraction and classification and identification technologies.

Fig. 1 is a flow chart diagram of a speech recognition method according to a first embodiment of the present disclosure.

As shown in fig. 1, a speech recognition method according to a first embodiment of the present disclosure includes:

s101, voice recognition is carried out on the voice information.

It should be noted that the execution subject of the speech recognition method of the embodiment of the present disclosure may be a hardware device having a data information processing capability and/or software necessary for driving the hardware device to operate. Alternatively, the execution body may include a workstation, a server, a computer, a user terminal and other intelligent devices. The user terminal includes, but is not limited to, a mobile phone, a computer, an intelligent voice interaction device, an intelligent household appliance, a vehicle-mounted terminal, and the like.

In the embodiments of the present disclosure, the speech recognition may be performed on the speech information in an offline and/or online manner, which is not limited herein.

In one embodiment, a voice recognition device may be previously installed on the smart device, and the voice recognition device performs voice recognition on the voice information, so as to implement offline voice recognition. Wherein the speech recognition means may comprise a speech recognition model.

In one embodiment, the intelligent device may establish a network connection with the server, the intelligent device may send the voice information to the server, perform voice recognition on the voice information through a voice recognition device in the server, and the server may send a voice recognition result to the intelligent device, so that online voice recognition may be implemented. The server may comprise a cloud server.

It should be noted that, in the embodiment of the present disclosure, the manner of acquiring the voice information is not limited too much. For example, a voice collecting device may be installed on the smart device or in a surrounding area of the smart device, and voice information may be collected by the voice collecting device. Wherein the voice collecting device may comprise a microphone.

S102, in response to the fact that the preset keywords are recognized from the voice information, the waiting time length of the tail point detection is updated to a second preset time length from a first preset time length, wherein the first preset time length is smaller than the second preset time length.

In the embodiment of the disclosure, in the process of performing voice recognition on the voice information, tail point detection can also be performed on the voice information. The tail-point detection result can be used to control whether to continue speech recognition on the speech information. For example, if the tail point detection result is that the tail point is not recognized, which indicates that the user speaking process is not finished, the control continues to perform speech recognition on the speech information. And if the tail point detection result is that the tail point is identified, indicating that the speaking process of the user is finished, controlling to stop carrying out voice identification on the voice information.

It should be noted that, in the embodiment of the present disclosure, the waiting time duration of tail point detection refers to a critical value for determining whether a tail point is currently identified in tail point detection. For example, if the mute duration in the voice information is shorter than the waiting duration of the tail point detection, the mute duration is shorter, the user speaking process is not finished, and the tail point detection result indicates that the tail point is not identified. On the contrary, if the mute duration in the voice information reaches the waiting duration of the tail point detection, the mute duration is too long, the user speaking process is finished, and the tail point detection result is that the tail point is identified.

In the embodiment of the disclosure, in response to recognizing the preset keyword from the voice information, the waiting duration of the tail point detection may be updated from the first preset duration to the second preset duration, and the first preset duration is less than the second preset duration, that is, when the preset keyword is recognized from the voice information, the waiting duration of the tail point detection may be extended.

The preset keywords can be set according to actual conditions, and are not limited too much. For example, the preset keywords include, but are not limited to, "navigate to," "call to," "turn up temperature to," and the like.

The first preset time length and the second preset time length can be set according to actual conditions, and excessive limitation is not performed here. For example, the first preset time period and the second preset time period are set to 200 milliseconds and 5 seconds, respectively.

For example, if the voice recognition result of the voice information is "navigate to", the end point detection duration may be updated from 200 milliseconds to 5 seconds in response to the recognition of the preset keyword from the voice information.

In summary, according to the voice recognition method of the embodiment of the present disclosure, in response to the recognition of the preset keyword from the voice information, the waiting duration of the end point detection is updated from the first preset duration to the second preset duration, where the first preset duration is smaller than the second preset duration. Therefore, when the preset keyword is recognized in the voice information, the waiting time of tail point detection is prolonged, the problem that the tail point is recognized due to the fact that the user pauses after the preset keyword is spoken can be avoided, the problem that the voice recognition process is interrupted due to the fact that the tail point is recognized can be avoided, the voice recognition time is prolonged, and the user use experience is improved.

Fig. 2 is a flow chart illustrating a speech recognition method according to a second embodiment of the present disclosure.

As shown in fig. 2, a speech recognition method according to a second embodiment of the present disclosure includes:

s201, performs speech recognition on the speech information.

S202, in response to the recognition of the preset keyword from the voice information, updating the waiting time length of the tail point detection from a first preset time length to a second preset time length, wherein the first preset time length is less than the second preset time length.

The relevant contents of steps S201-S202 can be referred to the above embodiments, and are not described herein again.

S203, continuing to perform tail point detection on the voice information according to the waiting time of the tail point detection to generate a tail point detection result.

In the embodiment of the disclosure, after the waiting duration of the tail point detection is updated from the first preset duration to the second preset duration, the waiting duration of the tail point detection at this time is the second preset duration, and the tail point detection is continuously performed on the voice information according to the waiting duration of the tail point detection to generate a tail point detection result.

In one embodiment, in the process of performing speech recognition on the speech information, tail point detection may be performed on the speech information according to a preset tail point detection strategy. The tail point detection strategy may include setting a value of a waiting time for tail point detection. Further, continuing to perform tail point detection on the voice information according to the waiting time of tail point detection, which may include updating a preset tail point detection strategy based on the waiting time of tail point detection, and continuing to perform tail point detection on the voice information according to the updated tail point detection strategy.

In an embodiment, the method continues to perform tail point detection on the voice information according to the waiting duration of the tail point detection to generate a tail point detection result, and may include starting timing from the initial time of the tail point detection to acquire the mute duration in the voice information, where the recognition mute duration is less than the waiting duration of the tail point detection, and the voice information includes a voice indicating that the mute duration is short, and the voice information includes a voice, and the user speaking process is not finished, and the generated tail point detection result is that the tail point is not recognized. Or, the identification mute duration reaches the waiting duration of the tail point detection, which indicates that the mute duration is too long and the user speaking process is finished, and the generated tail point detection result is the identification tail point. Therefore, the method can comprehensively consider the size relationship between the mute duration and the waiting duration of the tail point detection and whether the voice information contains the voice or not to generate the tail point detection result.

It is understood that the initial time of the tail point detection refers to a start time of tail point detection for voice information. Timing can be started from the initial moment of tail point detection, and the mute duration in the voice information is obtained. The initial time of the tail point detection can be set according to the actual situation, and is not limited too much here. For example, the initial time of speech recognition may be used as the initial time of end point detection, for example, the initial time of speech recognition is 10 dots, 10 minutes and 10 seconds, and the initial time of end point detection may be set to 10 dots, 10 minutes and 10 seconds.

In one embodiment, the initial time of the tail point detection can be updated based on the time of recognizing the preset keyword from the voice information, so that the initial time of the tail point detection can be updated in real time based on the time of recognizing the preset keyword from the voice information, and the initial time of the tail point detection is more flexible.

Optionally, the time when the last recognition unit of the preset keyword is recognized from the voice information may be used as the initial time of the tail point detection. The identification unit may be set according to actual situations, and is not limited herein, for example, the identification unit includes but is not limited to words, and the like.

For example, if the speech recognition result of the speech information is "navigate to", and the recognition unit is a word, the recognition time of "to" can be used as the initial time of the end point detection. For example, if the initial time of the original end point detection is 10 o 'clock 10 min 10 sec, and the recognition time of "arrival" is 10 o' clock 10 min 20 sec, the initial time of the end point detection can be updated from 10 o 'clock 10 min 10 sec to 10 o' clock 10 min 20 sec.

Further, the timing may be started from 10 minutes and 20 seconds of the initial time of the tail point detection, and the mute duration in the voice information may be obtained. It is understood that after the user speaks "navigate to", the user may pause due to considerations, environmental interference, and the like, and a mute section appears in the voice message, and the mute duration refers to the duration of the mute section. For example, if the user wants to say "navigate to a hotel" and may pause for 2 seconds between "to" and "wine", the recognition time of "to" is 10 o 'clock, 10 min and 20 seconds (i.e., the initial time of tail point detection), the recognition time of "wine" is 10 o' clock, 10 min and 22 seconds, the timing may be started from 10 o 'clock, 10 min and 20 seconds of tail point detection, the timing may be ended from 10 o' clock, 22 seconds of voice recognition (i.e., the recognition time of "wine"), and the duration of silence in the acquired voice message may be 2 seconds. In the related art, the waiting time for tail point detection is short, generally 200 ms, and at this time, when the mute duration reaches 200 ms, a tail point detection result is generated, and the tail point detection result is that a tail point is identified.

In the embodiment of the disclosure, the waiting time of tail point detection can be prolonged, for example, the waiting time of tail point detection is prolonged from 200 milliseconds to 5 seconds, the recognizable mute duration is less than the waiting time of tail point detection, the voice information contains voice, and the generated tail point detection result is that the tail point is not recognized, so that the problem that the tail point is recognized due to pause after the user speaks the preset keyword can be avoided.

In summary, according to the voice recognition method of the embodiment of the present disclosure, after the waiting duration of the tail point detection is updated from the first preset duration to the second preset duration, the tail point detection of the voice information may be continued according to the waiting duration of the tail point detection, so as to generate a tail point detection result. Therefore, when the preset keyword is recognized in the voice information, the waiting time of tail point detection is prolonged, the tail point detection of the voice information is continued according to the prolonged waiting time of the tail point detection, the generated tail point detection result is more humanized, and the problem that the tail point is recognized due to pause after the user speaks the preset keyword can be avoided.

Fig. 3 is a flowchart illustrating a speech recognition method according to a third embodiment of the present disclosure.

As shown in fig. 3, a speech recognition method according to a third embodiment of the present disclosure includes:

s301, performs speech recognition on the speech information.

S302, in response to the recognition of the preset keyword from the voice message, updating the waiting time of the tail point detection from a first preset time to a second preset time, wherein the first preset time is less than the second preset time.

S303, continuously carrying out tail point detection on the voice information according to the waiting time of the tail point detection to generate a tail point detection result.

The relevant contents of steps S301 to S303 can be referred to the above embodiments, and are not described herein again.

S304, responding to the tail point detection result that the tail point is not identified, and controlling to continue carrying out voice identification on the voice information.

And S305, in response to the detection result of the tail point being that the tail point is recognized, controlling to stop performing voice recognition on the voice information.

In the embodiment of the disclosure, after the tail point detection result is generated, whether to continue voice recognition on the voice information may be controlled according to the tail point detection result.

In one embodiment, in response to the end point detection result being that no end point is identified, indicating that the user speaking process is not finished, the control unit may continue to perform speech recognition on the speech information. And if the tail point detection result is that the tail point is identified, indicating that the speaking process of the user is finished, controlling to stop carrying out voice identification on the voice information.

In one embodiment, controlling to continue voice recognition on the voice information may include controlling to continue sending the voice information collected by the voice collecting device to the voice recognition device and controlling the voice recognition device to continue voice recognition on the voice information.

In one embodiment, the controlling to stop performing the voice recognition on the voice information may include controlling to stop sending the voice information collected by the voice collecting device to the voice recognition device, and controlling the voice recognition device to stop performing the voice recognition on the voice information. Therefore, the collected voice information can be stopped being sent to the voice recognition device when the tail point is recognized, and the transmission bandwidth can be saved.

In an embodiment, after the tail point detection result is generated, the waiting time for tail point detection may be updated from the second preset time to the first preset time in response to that the tail point detection result is that the tail point is not identified, that is, the waiting time for tail point detection may be shortened when the tail point detection result is that the tail point is not identified, which is beneficial to improving the sensitivity of tail point detection, and the tail point detection may be continued on the voice information according to the shortened waiting time for tail point detection to generate the tail point detection result.

For example, if the user wants to say "navigate to hotel", and the voice recognition result of the voice information is "navigate to", the waiting time for detecting the end point may be updated from 200 ms to 5 s in response to the preset keyword being recognized from the voice information, if the voice information continues to be detected for the end point according to the waiting time for detecting the end point of 5 s, the generated end point detection result is that the end point is not recognized, which indicates that the silence duration of the voice information is less than 5 s, and the voice information includes human voice, the waiting time for detecting the end point may be updated from 5 s to 200 ms, and the voice information continues to be detected for the end point according to the waiting time for detecting the end point of 200 ms.

In summary, according to the voice recognition method of the embodiment of the present disclosure, after the tail point detection result is generated, in response to that the tail point detection result is that the tail point is not recognized, the voice recognition of the voice information is controlled to continue. Or, in response to the tail point detection result that the tail point is identified, stopping voice identification of the voice information is controlled, and the method is beneficial to saving computing resources.

Fig. 4 is a block diagram of a speech recognition apparatus according to a first embodiment of the present disclosure.

As shown in fig. 4, a speech recognition apparatus 400 according to an embodiment of the present disclosure includes: an identification module 401 and an update module 402.

The recognition module 401 is configured to perform voice recognition on the voice information;

an updating module 402, configured to update a waiting duration of the end point detection from a first preset duration to a second preset duration in response to recognizing a preset keyword from the voice information, where the first preset duration is smaller than the second preset duration.

In one embodiment of the present disclosure, the speech recognition apparatus 400 further includes: a detection module to: and continuously carrying out tail point detection on the voice information according to the waiting time of the tail point detection to generate a tail point detection result.

In an embodiment of the present disclosure, the detection module is further configured to: timing from the initial time of tail point detection to obtain the mute duration in the voice information; recognizing that the mute duration is less than the waiting duration of the tail point detection, the voice information comprises voice, and the generated tail point detection result is that the tail point is not recognized; or recognizing that the mute duration reaches the waiting duration of the tail point detection, and generating the tail point detection result as recognizing the tail point.

In an embodiment of the present disclosure, the update module 402 is further configured to: and updating the initial moment of the tail point detection based on the moment of recognizing the preset keyword from the voice information.

In an embodiment of the present disclosure, the update module 402 is further configured to: and taking the moment of recognizing the last recognition unit of the preset keyword from the voice information as the initial moment of detecting the tail point.

In one embodiment of the present disclosure, the speech recognition apparatus 400 further includes: a control module to: responding to the tail point detection result that the tail point is not recognized, and controlling to continue voice recognition on the voice information; or, in response to the tail point detection result being that the tail point is recognized, controlling to stop performing voice recognition on the voice information.

In an embodiment of the present disclosure, the update module 402 is further configured to: and in response to the tail point detection result that the tail point is not identified, updating the waiting time length of the tail point detection from the second preset time length to the first preset time length.

In summary, the voice recognition apparatus according to the embodiment of the present disclosure can update the waiting duration of the end point detection from the first preset duration to the second preset duration in response to the recognition of the preset keyword from the voice information, where the first preset duration is smaller than the second preset duration. Therefore, when the preset keyword is recognized in the voice information, the waiting time of tail point detection is prolonged, the problem that the tail point is recognized due to the fact that the user pauses after the preset keyword is spoken can be avoided, the problem that the voice recognition process is interrupted due to the fact that the tail point is recognized can be avoided, the voice recognition time is prolonged, and the user use experience is improved.

In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations and do not violate the good customs of the public order.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

FIG. 5 illustrates a schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 5, the apparatus 500 comprises a computing unit 501 which may perform various appropriate actions and processes in accordance with a computer program stored in a Read Only Memory (ROM)502 or a computer program loaded from a storage unit 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The calculation unit 501, the ROM 502, and the RAM 503 are connected to each other by a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

A number of components in the device 500 are connected to the I/O interface 505, including: an input unit 506 such as a keyboard, a mouse, or the like; an output unit 507 such as various types of displays, speakers, and the like; a storage unit 508, such as a magnetic disk, optical disk, or the like; and a communication unit 509 such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.

The computing unit 501 may be a variety of general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 501 performs the respective methods and processes described above, such as a voice recognition method. For example, in some embodiments, the speech recognition method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 500 via the ROM 502 and/or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the speech recognition method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the speech recognition method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.

According to an embodiment of the present disclosure, there is also provided a computer program product including a computer program, wherein the computer program, when executed by a processor, implements the steps of the speech recognition method according to the above-mentioned embodiment of the present disclosure.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.