阅读说明：本技术 音频信号调节方法、装置、存储介质及终端 (Audio signal adjusting method and device, storage medium and terminal ) 是由 许钊铵 严锋贵 甘高亭 郑志勇 杨海 于 2017-08-18 设计创作，主要内容包括：音频信号调节方法、装置、存储介质及终端。该方法包括：检测到预设事件被触发时,控制麦克风采集音频信号(101),预设事件包括预设通话事件和/或预设录音事件；对音频信号对应的声音响度进行分析(102)；根据分析结果以及预设调节策略对音频信号对应的声音响度进行动态调节(103)；根据预设事件的类型对调节后的音频信号进行相应的输出处理。无需通话对端自行调节音量或者无需在播放录音时由收听者反复调节音量,可保持音频信号以预先设定好的音量变化规律被输出。(Audio signal adjusting method, device, storage medium and terminal. The method comprises the following steps: when a preset event is detected to be triggered, controlling a microphone to collect an audio signal (101), wherein the preset event comprises a preset call event and/or a preset recording event; analyzing (102) the sound loudness corresponding to the audio signal; dynamically adjusting the sound loudness corresponding to the audio signal according to the analysis result and a preset adjustment strategy (103); and carrying out corresponding output processing on the adjusted audio signal according to the type of the preset event. The volume is not required to be adjusted by the opposite end of the call or repeatedly adjusted by a listener when the recording is played, and the audio signal can be kept to be output according to the preset volume change rule.)

A method of audio signal conditioning, comprising:

when a preset event is detected to be triggered, controlling a microphone to collect an audio signal, wherein the preset event comprises a preset call event and/or a preset recording event;

analyzing the sound loudness corresponding to the audio signal;

dynamically adjusting the sound loudness corresponding to the audio signal according to the analysis result and a preset adjustment strategy;

and carrying out corresponding output processing on the adjusted audio signal according to the type of the preset event.

The method according to claim 1, wherein the performing the corresponding output processing on the adjusted audio signal according to the type of the preset event comprises:

when the preset event comprises a preset call event, sending the adjusted audio signal to a call opposite terminal;

and when the preset event comprises a preset recording event, storing the adjusted audio signal as a recording signal.

The method of claim 2, wherein analyzing the sound loudness corresponding to the audio signal comprises:

and analyzing the amplitude information of the audio signal to obtain a sound loudness analysis result.

The method of claim 3, wherein analyzing the amplitude information of the audio signal to obtain a sound loudness analysis result comprises:

extracting amplitude information of the corresponding voice in the audio signal;

and analyzing the amplitude information of the corresponding human voice to obtain a voice loudness analysis result.

The method according to claim 3 or 4, wherein the dynamically adjusting the sound loudness corresponding to the audio signal according to the analysis result and a preset adjustment strategy comprises:

when the sound loudness analysis result comprises that the current sound loudness is smaller than a first preset loudness threshold value, increasing and adjusting the current sound loudness; and/or the presence of a gas in the gas,

and when the sound loudness analysis result comprises that the current sound loudness is greater than a second preset loudness threshold value, reducing and adjusting the current sound loudness.

The method of claim 5,

when the sound loudness analysis result includes that the current sound loudness is smaller than a first preset loudness threshold, performing rise adjustment on the current sound loudness includes:

when a current amplitude value in the audio signal is smaller than a first preset amplitude threshold value, adjusting the current amplitude value to a corresponding first target amplitude, wherein the first target amplitude is larger than or equal to the first preset amplitude threshold value;

when the sound loudness analysis result includes that the current sound loudness is greater than a second preset loudness threshold, performing reduction adjustment on the current sound loudness includes:

when the current amplitude value in the audio signal is larger than a second preset amplitude threshold value, adjusting the current amplitude value to a corresponding second target amplitude, wherein the second target amplitude is smaller than or equal to the second preset amplitude threshold value.

The method of claim 6,

the adjusting the current amplitude value to a corresponding first target amplitude comprises:

determining a corresponding first target amplitude according to the current amplitude value and a first preset corresponding relation;

determining a corresponding first gain adjustment parameter value according to the first target amplitude and the current amplitude value;

utilizing the first gain adjustment parameter value to perform signal gain adjustment on the position, corresponding to the current amplitude value, in the audio signal;

the adjusting the current sound loudness to a corresponding second target loudness includes:

determining a corresponding second target amplitude according to the current amplitude value and a second preset corresponding relation;

determining a corresponding second gain adjustment parameter value according to the current amplitude value and the second target amplitude;

and performing signal gain adjustment on the position, corresponding to the second amplitude value, in the audio signal by using the second gain adjustment parameter value.

The method of claim 7,

before determining the corresponding first target amplitude according to the current amplitude value and the first preset corresponding relation, the method further includes:

selecting a first preset corresponding relation from a plurality of candidate first preset corresponding relations according to a first preset reference factor;

before determining a corresponding second target amplitude according to the current amplitude value and a second preset corresponding relation, the method further includes:

and selecting a second preset corresponding relation from the plurality of candidate second preset corresponding relations according to a second preset reference factor.

The method of claim 8, wherein when the predetermined event is a predetermined talk event,

the selecting a first preset corresponding relation from the candidate first preset corresponding relations according to the first preset reference factor includes:

acquiring attribute information of a contact of a call opposite terminal and/or contextual model information of the call opposite terminal;

selecting a first preset corresponding relation from a plurality of candidate first preset corresponding relations according to the attribute information and/or the contextual model information;

the selecting a second preset corresponding relation from the plurality of candidate second preset corresponding relations according to a second preset reference factor includes:

acquiring attribute information of a contact of a call opposite terminal and/or contextual model information of the call opposite terminal;

and selecting a second preset corresponding relation from a plurality of candidate second preset corresponding relations according to the attribute information and/or the contextual model information.

An audio signal conditioning apparatus, comprising:

the microphone comprises an audio signal acquisition module, a voice recognition module and a voice recognition module, wherein the audio signal acquisition module is used for controlling the microphone to acquire an audio signal when a preset event is detected to be triggered, and the preset event comprises a preset call event and/or a preset recording event;

the loudness analysis module is used for analyzing the sound loudness corresponding to the audio signal;

the loudness adjusting module is used for dynamically adjusting the sound loudness corresponding to the audio signal according to the analysis result and a preset adjusting strategy;

and the signal output module is used for carrying out corresponding output processing on the adjusted audio signal according to the type of the preset event.

The apparatus of claim 10, wherein the signal output module is configured to:

when the preset event comprises a preset call event, sending the adjusted audio signal to a call opposite terminal;

and when the preset event comprises a preset recording event, storing the adjusted audio signal as a recording signal.

The apparatus of claim 11, wherein the pair loudness analysis module is configured to:

and analyzing the amplitude information of the audio signal to obtain a sound loudness analysis result.

The apparatus of claim 12, wherein the pair loudness analysis module is configured to:

extracting amplitude information of the corresponding voice in the audio signal;

and analyzing the amplitude information of the corresponding human voice to obtain a voice loudness analysis result.

The apparatus of claim 11 or 12, wherein the loudness adjustment module is configured to:

when the sound loudness analysis result comprises that the current sound loudness is smaller than a first preset loudness threshold value, increasing and adjusting the current sound loudness; and/or the presence of a gas in the gas,

and when the sound loudness analysis result comprises that the current sound loudness is greater than a second preset loudness threshold value, reducing and adjusting the current sound loudness.

The apparatus of claim 14,

when the sound loudness analysis result includes that the current sound loudness is smaller than a first preset loudness threshold, performing rise adjustment on the current sound loudness includes:

when a current amplitude value in the audio signal is smaller than a first preset amplitude threshold value, adjusting the current amplitude value to a corresponding first target amplitude, wherein the first target amplitude is larger than or equal to the first preset amplitude threshold value;

when the sound loudness analysis result includes that the current sound loudness is greater than a second preset loudness threshold, performing reduction adjustment on the current sound loudness includes:

when the current amplitude value in the audio signal is larger than a second preset amplitude threshold value, adjusting the current amplitude value to a corresponding second target amplitude, wherein the second target amplitude is smaller than or equal to the second preset amplitude threshold value.

The apparatus of claim 15,

the adjusting the current amplitude value to a corresponding first target amplitude comprises:

determining a corresponding first target amplitude according to the current amplitude value and a first preset corresponding relation;

determining a corresponding first gain adjustment parameter value according to the first target amplitude and the current amplitude value;

utilizing the first gain adjustment parameter value to perform signal gain adjustment on the position, corresponding to the current amplitude value, in the audio signal;

the adjusting the current sound loudness to a corresponding second target loudness includes:

determining a corresponding second target amplitude according to the current amplitude value and a second preset corresponding relation;

determining a corresponding second gain adjustment parameter value according to the current amplitude value and the second target amplitude;

and performing signal gain adjustment on the position, corresponding to the second amplitude value, in the audio signal by using the second gain adjustment parameter value.

The apparatus of claim 16, wherein the loudness adjustment module is further configured to:

before determining a corresponding first target amplitude according to the current amplitude value and a first preset corresponding relation, selecting a first preset corresponding relation from a plurality of candidate first preset corresponding relations according to a first preset reference factor; and/or the presence of a gas in the gas,

and before determining the corresponding second target amplitude according to the current amplitude value and the second preset corresponding relation, selecting the second preset corresponding relation from a plurality of candidate second preset corresponding relations according to a second preset reference factor.

The apparatus of claim 17, wherein when the predetermined event is a predetermined talk event,

the selecting a first preset corresponding relation from the candidate first preset corresponding relations according to the first preset reference factor includes:

acquiring attribute information of a contact of a call opposite terminal and/or contextual model information of the call opposite terminal;

selecting a first preset corresponding relation from a plurality of candidate first preset corresponding relations according to the attribute information and/or the contextual model information;

the selecting a second preset corresponding relation from the plurality of candidate second preset corresponding relations according to a second preset reference factor includes:

acquiring attribute information of a contact of a call opposite terminal and/or contextual model information of the call opposite terminal;

and selecting a second preset corresponding relation from a plurality of candidate second preset corresponding relations according to the attribute information and/or the contextual model information.

A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the audio signal conditioning method as claimed in any one of claims 1 to 9.

A terminal comprising a microphone, a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the computer program, implements the audio signal conditioning method of any of claims 1-7.