阅读说明：本技术 音频编码方法、装置、电子设备和存储介质 (Audio encoding method, audio encoding device, electronic equipment and storage medium ) 是由 郑羲光 董培 陈翔宇 张晨 于 2020-06-15 设计创作，主要内容包括：本公开提供音频编码方法、装置、电子设备和存储介质。该方法包括：获取待编码音频信号的特征信息；根据所述特征信息确定所述待编码音频信号的音频类型信息；根据所述音频类型信息,确定所述待编码音频信号的编码码率；利用所述编码码率对所述待编码音频信号进行编码。由此,本公开选用的编码码率是与音频类型信息匹配的码率。解决了传统技术中在编码过程中指定的编码码率不合理容易导致浪费带宽资源的问题。(The present disclosure provides an audio encoding method, apparatus, electronic device, and storage medium. The method comprises the following steps: acquiring characteristic information of an audio signal to be encoded; determining audio type information of the audio signal to be coded according to the characteristic information; determining the coding rate of the audio signal to be coded according to the audio type information; and encoding the audio signal to be encoded by using the encoding code rate. Therefore, the coding rate selected by the method is the code rate matched with the audio type information. The problem that bandwidth resources are wasted due to the fact that the designated coding rate is unreasonable in the coding process in the traditional technology is solved.)

1. An audio encoding method, characterized in that the method comprises:

acquiring characteristic information of an audio signal to be encoded;

determining audio type information of the audio signal to be coded according to the characteristic information;

determining the coding rate of the audio signal to be coded according to the audio type information;

and encoding the audio signal to be encoded by using the encoding code rate.

2. The method according to claim 1, wherein said determining audio type information of the audio signal to be encoded according to the feature information comprises:

inputting the characteristic information into a neural network;

processing the characteristic information by using the neural network to obtain the probability that the audio signal to be coded belongs to various audio types respectively;

and determining the audio type information of the audio signal to be coded according to the probability that the audio signal to be coded belongs to each audio type respectively.

3. The method according to claim 2, wherein the determining the audio type information of the audio signal to be encoded according to the probability that the audio signal to be encoded belongs to each audio type respectively comprises:

determining the audio type information corresponding to the audio type with the maximum probability as the audio type information of the audio signal to be coded;

determining the coding rate of the audio signal to be coded according to the audio type information includes:

and searching the coding rate corresponding to the audio type information, and taking the searched coding rate as the coding rate of the audio signal to be coded.

4. The method of claim 2, wherein the determining the coding rate of the audio signal to be coded according to the audio type information comprises:

taking the probability that the audio signals to be coded respectively belong to various audio types as an adjustment factor;

acquiring coding rates corresponding to various audio types;

and carrying out weighted summation according to the coding rate and the adjustment factor of each audio type to obtain the coding rate of the audio signal to be coded.

5. The method according to claim 2, wherein before the obtaining the feature information of the audio signal to be encoded, the method further comprises:

training the neural network by:

acquiring an audio type training sample, wherein the audio type training sample comprises characteristic information of audio signals of the same audio type and labeled audio type information;

and training the neural network according to the audio type training sample.

6. The method of claim 1, wherein determining the audio signal to be encoded comprises:

segmenting an audio signal to be processed;

determining each obtained audio signal segment as the audio signal to be encoded.

7. The method according to claim 1, wherein the obtaining the feature information of the audio signal to be encoded comprises:

converting the audio signal to be coded into a frequency domain to obtain a frequency domain signal;

performing feature extraction on the frequency domain signal to obtain preset feature information, wherein the preset feature information comprises a Mel cepstrum and/or a Mel frequency spectrum;

and determining the frequency domain signal and/or the preset characteristic information as the characteristic information of the audio signal to be coded.

8. An audio encoding apparatus, characterized in that the apparatus comprises:

an acquisition module configured to perform acquisition of feature information of an audio signal to be encoded;

an audio type information determination module configured to perform determining audio type information of the audio signal to be encoded according to the feature information;

an encoding code rate determination module configured to determine an encoding code rate of the audio signal to be encoded according to the audio type information;

an encoding module configured to perform encoding of the audio signal to be encoded with the encoding rate.

9. An electronic device comprising 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; the instructions are executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A computer storage medium, characterized in that the computer storage medium stores a computer program for performing the method according to any one of claims 1-7.