Method and device for improving audio processing performance

Patent metadata

Field	Value
Publication number	US-10522164-B2
Application number	US-201715664857-A
Country	US
Kind code	B2
Filing date	Jul 31, 2017
Priority date	May 12, 2015
Publication date	Dec 31, 2019
Grant date	Dec 31, 2019

Abstract

A method and a device for improving audio processing performance are provided. In some embodiments, the method includes: acquiring audio data in an audio call in a terminal; processing the audio data by utilizing an audio processing algorithm, to obtain a characteristic parameter of the audio data; analyzing the processing quality of the audio data according to the characteristic parameter of the audio data; and if the processing quality of the audio data does not reach a preset quality standard, optimizing the audio processing algorithm by utilizing optimization data matching the terminal.

First claim

The invention claimed is:

1. A method for improving audio processing performance, comprising:
using a hardware processor on a terminal:
acquiring audio data of an audio call in the terminal;
performing first processing on the audio data by utilizing an audio processing algorithm and obtaining a characteristic parameter of the audio data;
sending, to a server, a report including the characteristic parameter; and
in response to a processing quality of the audio data not having reached a preset quality standard, the processing quality of the audio data determined by analyzing the processing quality of the audio data based on the characteristic parameter of the audio data:
receiving from the server, a request for a model characteristic for the terminal, the model characteristic comprising information on a hardware component of the terminal;
receiving optimization data from the server, the optimization data matching the model characteristic, the optimization data matching the model characteristic obtained by searching a database for the optimization data matching the model characteristic;
optimizing the audio processing algorithm by utilizing optimization data matching the terminal; and
performing second processing on the audio data using the audio processing algorithm after optimizing the audio processing algorithm,

wherein the audio processing algorithm comprises at least one of an echo cancellation algorithm, a noise reduction algorithm and a volume processing gain algorithm;
wherein the characteristic parameter of the audio data comprises at least one of an echo parameter, a noise parameter and a gain parameter;
wherein the echo parameter comprises an echo processing duration, an echo roundtrip loss and an echo roundtrip loss enhancement;
wherein the noise parameter comprises an input signal-to-noise ratio and an output signal-to-noise ratio;
wherein the gain parameter comprises an input digital envelope of volume and an output digital envelope of volume.

2. The method according to claim 1 , wherein the acquiring audio data of an audio call in a terminal comprises:
collecting voice information in the audio call during the audio call; and
converting the voice information into the audio data.

3. The method according to claim 1 , wherein the first processing the audio data by utilizing the audio processing algorithm and obtaining a characteristic parameter of the audio data comprises any one or a combination of:
performing an echo cancellation process on the audio data by utilizing the echo cancellation algorithm, and recording an echo parameter obtained during the echo cancellation process;
performing a noise reduction process on the audio data by utilizing the noise reduction algorithm, and calculating a noise parameter based on the noise reduction process; and
performing a volume gain process on the audio data by utilizing the volume gain processing algorithm, and counting a gain parameter based on the volume gain process.

4. The method according to claim 3 , wherein the analyzing a processing quality of the audio data based on the characteristic parameter of the audio data comprises any one or a combination of:
determining an echo cancellation degree of the audio data based on the echo processing duration, the echo roundtrip loss and the echo roundtrip loss enhancement;
determining a noise magnitude of the audio data before the noise reduction process based on the input signal-to-noise ratio, and determining a noise magnitude of the audio data after the noise reduction process based on the output signal-to-noise ratio; and
determining an original volume of the audio data based on the input digital envelope, and determining a gain volume of the audio data based on the output digital envelope.

5. The method according to claim 4 , wherein:
the preset quality standard comprises at least one of a preset range of echo cancellation degree, a preset range of noise, and a preset range of gain volume; and
the audio data processing quality reaches the preset quality standard if at least one of the following conditions is met: the echo cancellation degree of the audio data is in the preset range of echo cancellation degree, the noise magnitude of the audio data after the noise reduction process is in the preset range of noise, and the gain volume of the audio data is in the preset range of gain volume.

6. The method according to claim 1 , where the hardware component of the terminal includes a core of the terminal, a sound card of the terminal, or both.

7. A device for improving audio processing performance, comprising at least one processor and a memory connected to the at least one processor, wherein the at least one processor is configured to execute program codes stored in the memory to perform the following operations:
acquiring audio data of an audio call in a terminal;
performing first processing on the audio data by utilizing an audio processing algorithm, and obtaining a characteristic parameter of the audio data;
sending, to a server, a report including the characteristic parameter; and
in response to a processing quality of the audio data not having reached a preset quality standard, the processing quality of the audio data determined by analyzing the processing quality of the audio data based on the characteristic parameter of the audio data:
receiving from the server, a request for a model characteristic for the terminal, the model characteristic comprising information on a hardware component of the terminal;
receiving optimization data from the server, the optimization data matching the model characteristic, the optimization data matching the model characteristic obtained by searching a database for the optimization data matching the model characteristic;
optimizing the audio processing algorithm by utilizing optimization data matching the terminal and;
performing second processing on the audio data using the audio processing algorithm after optimizing the audio processing algorithm,

wherein the audio processing algorithm comprises at least one of an echo cancellation algorithm, a noise reduction algorithm and a volume gain processing algorithm;
wherein the characteristic parameter of the audio data comprises at least one of an echo parameter, a noise parameter and a gain parameter;
wherein the echo parameter comprises an echo processing duration, an echo roundtrip loss and an echo roundtrip loss enhancement;
wherein the noise parameter comprises an input signal-to-noise ratio and an output signal-to-noise ratio; and
wherein the gain parameter comprises an input digital envelope of volume and an output digital envelope of volume.

8. The device according to claim 7 , wherein the operations further comprise:
collecting voice information in the audio call during the audio call; and
converting the voice information into the audio data.

9. The device according to claim 7 , wherein the operations further comprise any one or a combination of:
performing an echo cancellation process on the audio data by utilizing the echo cancellation algorithm, and recording an echo parameter obtained during the echo cancellation process;
performing a noise reduction process on the audio data by utilizing the noise reduction algorithm, and calculating a noise parameter based on the noise reduction process; and
performing a volume gain process on the audio data by utilizing the volume gain processing algorithm, and counting a gain parameter based on the volume gain process.

10. The device according to claim 9 , wherein the operations further comprise any one or a combination of:
determining an echo cancellation degree of the audio data based on the echo processing duration, the

Assignees

• Tencent Tech Shenzhen Co Ltd
• Tencent Tech Shenzhen Company Llmited

Inventors

• Zhang Dingyuan
• Li Junming
• Peng Yuanjiang
• Li Guangfa
• Tang Yongchun

Classifications

• G10L25/60

  for measuring the quality of voice signals · CPC title

• H04M3/002

  Applications of echo suppressors or cancellers in telephonic connections (in two-way loud-speaking telephone systems H04M9/08, echo suppressors or cancellers per se H04B3/20) · CPC title

• G10L2021/02082

  the noise being echo, reverberation of the speech · CPC title

• H04M3/2236

  Quality of speech transmission monitoring · CPC title

• G10L21/0232

  Processing in the frequency domain · CPC title