SPEECH DATA RECOGNITION METHOD, APPARATUS, AND SERVER FOR DISTINGUISHING REGIONAL ACCENT

• US 20160284344A1
• Filed: 12/18/2014
• Published: 09/29/2016
• Est. Priority Date: 12/19/2013
• Status: Active Grant

• Current Assignee: Baidu Online Network Technology (Beijing) Co., Ltd (Baidu Incorporated)
• Original Assignee: Baidu Online Network Technology (Beijing) Co., Ltd (Baidu Incorporated)
• Inventors: Yin, Zhao, Su, Dan
• Granted Patent: US 9,928,831 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/005 Language recognition
• CPC Class Codes: G10L 15/01 Assessment or evaluation of speech recognition systems
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• CPC Class Codes: G10L 15/07 to the speaker
• CPC Class Codes: G10L 25/84 for discriminating voice from noise
• CPC Class Codes: G10L 25/90 Pitch determination of speech signals

Abstract

A speech data recognition method, apparatus, and server are for distinguishing regional accent. The speech data recognition method includes: calculating a speech recognition confidence and/or a signal-to-noise ratio of the speech data, and screening a regional speech data from the speech data based on the speech recognition confidence and/or the signal-to-noise ratio of the speech dat; and determining a region to which the regional speech data belongs based on a regional attribute of the regional speech data. The regional speech data are automatically recognized from the mass speech data by calculating the speech recognition confidence, the signal-to-noise ratio of the speech data or the combination thereof, thereby avoiding manual labeling of the speech data and enhancing the efficiency of the speech data processing.

Claims

1. A speech data recognition method for distinguishing regional accents, comprising:

calculating a speech recognition confidence, a signal-to-noise ratio of a speech data, or a combination thereof;

screening a regional speech data from the speech data based on the speech recognition confidence, the signal-to-noise ratio, or the combination thereof; and

determining a region to which the regional speech data belongs based on a regional attribute of the regional speech data.

2. The method according to claim 1, wherein the calculating and screening steps comprises:

calculating the speech recognition confidence of the speech data;

selecting the speech data with a mid-range speech recognition confidence;

calculating the signal-to-noise ratio of the selected speech data, and

selecting the speech data whose signal-to-noise ratio is greater than a preset threshold as the regional speech data.

3. The method according to claim 1, wherein the regional attribute includes a location corresponding to a source IP address of the speech data, or a location corresponding to a source user of the speech data.

4. The method according to claim 1, wherein the calculating the speech recognition confidence of the speech data comprises:

calculating the speech recognition confidence of the speech data based on likelihood, state residing information, and/or likelihood ratio of the speech data, or a combination thereof.

5. The method according to claim 2, wherein the mid-range is about 30% to about 80%.

6. The method according to claim 1, wherein the calculating the signal-to-noise ratio of the speech data comprises:

extracting a fundamental tone data of the speech data by using a fundamental tone extracting algorithm;

obtaining a noise data of the speech data based on the extracted fundamental tone data; and

calculating the signal-to-noise ratio of the speech data based on the fundamental tone data and the noise data.

7. The method according to claim 6, wherein the fundamental tone extracting algorithm comprises at least one of a spectral subtraction, a Wiener-filtration, or a short-term spectrum minimum mean square error estimation method.

8. A speech data recognition apparatus for distinguishing regional accents, comprising:

a speech data screening module configured to

calculate a speech recognition confidence, a signal-to-noise ratio of the speech data, or a combination thereof, and

screen a regional speech data from the speech data based on the speech recognition confidence, the signal-to-noise ratio, or the combination thereof; and

a region determining module configured to determine a region to which the regional speech data belongs based on a regional attribute of the regional speech data.

9. The apparatus according to claim 8, wherein the speech data screening module comprises:

a confidence selecting sub-module configured to;

calculate the speech recognition confidence of the speech data, and

select the speech data with a mid-range speech recognition confidence; and

a signal-to-noise ratio selecting sub-module configured to;

calculate the signal-to-noise ratio of the selected speech data, and

select the speech data whose signal-to-noise ratio is greater than a preset threshold as the regional speech data.

10. The apparatus according to claim 8, wherein the regional attribute comprises a location corresponding to a source IP address of the speech data, or a location corresponding to a source user of the speech data.

11. The apparatus according to claim 8, wherein the speech data screening module is configured to calculate the speech recognition confidence of the speech data based on likelihood, state residing information, likelihood ratio of the speech data, or a combination thereof.

12. The apparatus according to claim 9, wherein the mid-range is about 30% to about 80%.

13. The apparatus according to claim 8, wherein the speech data screening module is configured to:

extract a fundamental tone data of the speech data by using a fundamental tone extracting algorithm;

obtain a noise data of the speech data according to the extracted fundamental tone data; and

calculate the signal-to-noise ratio of the speech data according to the fundamental tone data and the noise data.

14. The apparatus according to claim 13, wherein the fundamental tone extracting algorithm comprises at least one of a spectral subtraction, a Wiener-filtration, or a short-term spectrum minimum mean square error estimation method.

15. A server for performing a speech data recognition for distinguishing regional accents, the server comprising:

a processor,

a memory, and

a computer program, wherein the computer program is stored in the memory, wherein the computer program is executed by the processor, and wherein the computer program comprises instructions for;

calculating a speech recognition confidence, a signal-to-noise ratio of a speech data, or a combination thereof, and screening a regional speech data from the speech data according to the speech recognition confidence, and/or the signal-to-noise ratio, or the combination thereof; and

determining a region to which the regional speech data belongs based on a regional attribute of the regional speech data.