# US 2016/0253995 A1 · Voice recognition method, voice recognition device, and electronic device

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2016/0253995 A1
- Document ID: US20160253995A1
- Status: Published application
- Kind: A1
- Application number: 15/149,599
- Filed: 2016-05-09
- Published: 2016-09-01
- Earliest claimed: 2013-11-14
- Assignees: Huawei Technologies Co., Ltd.
- Applicants: Huawei Technologies Co., Ltd.
- Inventors: Junyang ZHOU
- Web page: https://patentgrep.com/patent/US20160253995A1

## CPC

- G10L 15/20: Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech (G10L21/02 takes precedence)
- G10L 21/02: Speech enhancement, e.g. noise reduction or echo cancellation (reducing echo effects in line transmission systems H04B3/20; echo suppression in hands-free telephones H04M9/08)
- G10L 21/0216: characterised by the method used for estimating noise
- G10L 21/0224: Processing in the time domain
- H04R 3/00: Circuits for transducers (arrangements for producing a reverberation or echo sound G10K15/08; amplifiers H03F)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- H04R: LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS (producing sounds with frequency not determined by supply frequency G10K)

## Abstract

A voice recognition method, a voice recognition device, and an electronic device. In this method, first determining is performed by using a sample environment corresponding to a detection voice and a previous environment type, so as to output a corresponding voice correction instruction to a voice engine; then, a to-be-recognized voice is input to the voice engine and a noise type detection engine at the same time, and the voice engine corrects the to-be-recognized voice by using the voice correction instruction, so that quality of an original voice is not impaired by noise processing, and a corresponding initial recognition result is output; the noise type detection engine determines a current environment type by using the to-be-recognized voice and a voice training sample under a different environment; finally, confidence of the initial recognition result is adjusted by using the current environment type.

## Claims

### Claim 1

A voice recognition method, comprising:
receiving, by a voice recognition device, an input voice, wherein the voice recognition device comprises a noise type detection engine, a storage area and a voice engine;
acquiring, by the voice recognition device, a detection voice and a to-be-recognized voice by dividing the input voice, wherein a length of voice data comprised in the detection voice is less than a length of voice data comprised in the to-be-recognized voice;
selecting, by the noise type detection engine after comparing the acquired detection voice with a voice training sample under a different sample environment, a sample environment corresponding to a voice training sample that has a minimum difference with the detection voice, as a detection environment type, wherein the sample environment comprises a quiet environment and a noise environment;
detecting, by the voice recognition device, a storage area;
outputting by the voice recognition device, when a recognizable previous environment type exists in the storage area, a voice correction instruction according to a result of comparison between the detection environment type and the previous environment type, wherein the previous environment type is a quiet environment or a noise environment;
controlling, by the voice engine according to the voice correction instruction, correction on the to-be-recognized voice, and outputting an initial recognition result;
separately comparing, by the noise type detection engine, the received to-be-recognized voice with a voice training sample under a different sample environment, and selecting a sample environment corresponding to a voice training sample that has a minimum difference with the to-be-recognized voice, as a current environment type;
storing, by the voice recognition device, the current environment type to the storage area, and abandoning the current environment type after preset duration; and
outputting, by the voice recognition device, a final recognition result after a confidence value of the initial recognition result is adjusted according to the current environment type.

### Claim 2 (depends on 1)

The method according to claim 1, wherein when the previous environment type is not recognized in the storage area, the method further comprises:
acquiring, by the voice recognition device, a pre-stored initial environment type, wherein the initial environment type comprises a quiet environment or a noise environment; and
determining, by the voice recognition device, according to the initial environment type and the detection environment type, and outputting the voice correction instruction.

### Claim 3 (depends on 2)

The method according to claim 2, wherein the determining, by the voice recognition device, according to the initial environment type and the detection environment type, and outputting the voice correction instruction comprises:
determining, by the voice recognition device, whether the initial environment type is the same as the detection environment type;
if the initial environment type is the same as the detection environment type, outputting by the voice recognition device, when both the initial environment type and the detection environment type are noise environments, a voice correction instruction used for voice quality enhancement, and outputting by the voice recognition device, when both the initial environment type and the detection environment type are quiet environments, a voice correction instruction used for disabling noise reduction processing; and
if the initial environment type is not the same as the detection environment type, outputting by the voice recognition device, when the initial environment type is a noise environment, a voice correction instruction used for voice quality enhancement, and outputting by the voice recognition device, when the initial environment type is a quiet environment, a voice correction instruction used for disabling noise reduction processing.

### Claim 4 (depends on 1)

The method according to claim 1, wherein the outputting by the voice recognition device, when a recognizable previous environment type exists in the storage area, a voice correction instruction according to a result of comparison between the detection environment type and the previous environment type comprises:
acquiring the previous environment type and effective impact duration T of the previous environment type on the input voice;
calculating a time difference t between time for inputting the detection voice and time for previously inputting a voice, and an impact value w(t) of the previous environment type on the detection environment type, wherein w(t) is a truncation function that decays with time t, a value of w(t) is obtained by training sample data of a voice training sample under a different sample environment, and values of t and T are positive integers;
determining a balance relationship between the previous environment type and the detection environment type;
outputting, when both the previous environment type and the detection environment type are noise environments, a voice correction instruction used for voice quality enhancement;
outputting, when both the previous environment type and the detection environment type are quiet environments, a voice correction instruction used for disabling noise reduction processing;
outputting, when the previous environment type is a noise environment, the detection environment type is a quiet environment, and w(t)>=0.5, a voice correction instruction used for voice quality enhancement;
outputting, when the previous environment type is a noise environment, the detection environment type is a quiet environment, and w(t)<0.5, a voice correction instruction used for disabling noise reduction processing; and
when the w(t)>T, outputting, when the detection environment type is a quiet environment, a voice correction instruction used for disabling noise reduction processing, and outputting, when the detection environment is a noise environment, a voice correction instruction used for voice quality enhancement.

### Claim 5 (depends on 1)

The method according to claim 1, wherein the separately comparing, by the noise type detection engine, the received to-be-recognized voice with a voice training sample under a different sample environment, and selecting a sample environment corresponding to a voice training sample that has a minimum difference with the to-be-recognized voice, as a current environment type comprises:
analyzing, by the noise type detection engine, a voice frame part and a noise frame part of the received to-be-recognized voice to acquire a noise level, a voice level, and a signal-to-noise ratio (SNR) of the to-be-recognized voice;
comparing the noise level, the voice level, and the SNR of the to-be-recognized voice with a noise training level, a voice training level, and a training SNR of a voice training sample under a different sample environment, respectively; and
determining that a sample environment corresponding to a noise training level that has a minimum difference with the noise level, a voice training level that has a minimum difference with the voice level, and a training SNR that has a minimum difference with the SNR is the current environment type.

### Claim 6 (depends on 1)

The method according to claim 1, wherein
the preset duration when the current environment type is a quiet environment is longer than the preset duration when the current environment type is a noise environment.

### Claim 7 (depends on 1)

The method according to claim 1, wherein the noise environment comprises: a vehicle-mounted low noise environment, a vehicle-mounted high noise environment, an ordinary roadside environment, a busy roadside environment, and a noisy environment.

### Claim 8

A voice recognition device, comprising:
a processor, configured to acquire a detection voice and a to-be-recognized voice by sampling an input voice, and input the detection voice and the to-be-recognized voice into a noise type detection engine and a voice engine at the same time; configured to detect a storage area, and output, when a recognizable previous environment type exists in the storage area, a voice correction instruction according to a result of comparison between a detection environment type output by the noise type detection engine and the previous environment type; and configured to output a final recognition result after a confidence value of an initial recognition result output by the voice engine is adjusted according to a current environment type output by the noise type detection engine, wherein a length of voice data comprised in the detection voice is less than a length of voice data comprised in the to-be-recognized voice, and the previous environment type is a quiet environment or a noise environment;
the noise type detection engine, configured to separately compare the detection voice and the to-be-recognized voice that are output by the processor with a voice training sample under a different sample environment; select a sample environment corresponding to a voice training sample that has a minimum difference with the detection voice, as a detection environment type; select a sample environment corresponding to a voice training sample that has a minimum difference with the to-be-recognized voice, as a current environment type; and store the current environment type to the storage area, and abandon the current environment type after preset duration; and
the voice engine, configured to control correction on the received to-be-recognized voice according to the voice correction instruction output by the processor, and output an initial recognition result.

### Claim 9 (depends on 8)

The device according to claim 8, wherein the processor, configured to detect a storage area, and output, when a recognizable previous environment exists in the storage area, a voice correction instruction according to a result of comparison between a detection environment type output by the noise type detection engine and the previous environment type comprises:
the processor, configured to acquire the previous environment type and effective impact duration T of the previous environment type on the input voice; calculate a time difference t between time for inputting the detection voice and time for previously inputting a voice, and an impact value w(t) of the previous environment type on the detection environment type; determine a balance relationship between the previous environment type and the detection environment type; output, when both the previous environment type and the detection environment type are noise environments a voice correction instruction used for voice quality enhancement; output, when both the previous environment type and the detection environment type are quiet environments, a voice correction instruction used for disabling noise reduction processing; output, when the previous environment type is a noise environment, the detection environment is a quiet environment, and w(t)>=0.5, a voice correction instruction used for voice quality enhancement; output, when the previous environment type is a noise environment, the detection environment is a quiet environment, and w(t)<0.5, a voice correction instruction used for disabling noise reduction processing; and when w(t)>T, output, when the detection environment type is a quiet environment, a voice correction instruction used for disabling noise reduction processing; and output, when the detection environment type is a noise environment, a voice correction instruction used for voice quality enhancement, wherein
w(t) is a truncation function that decays with time t, a value of w(t) is obtained by training sample data of a voice training sample under a different sample environment, and values of t and T are positive integers.

### Claim 10 (depends on 8)

The device according to claim 8, wherein the noise type detection engine, configured to compare the to-be-recognized voice output by the processor with a voice training sample under a different sample environment; select a sample environment corresponding to a voice training sample that has a minimum difference with the to-be-recognized voice, as a current environment type comprises:
the noise type detection engine, configured to analyze a voice frame part and a noise frame part of the received to-be-recognized voice to acquire a noise level, a voice level, and a signal-to-noise ratio (SNR) of the to-be-recognized voice; compare the noise level, the voice level, and the SNR of the to-be-recognized voice with a noise training level, a voice training level, and a training SNR of a voice training sample under a different sample environment, respectively; and determine that a sample environment corresponding to a noise training level that has a minimum difference with the noise level, a voice training level that has a minimum difference with the voice level, and a training SNR that has a minimum difference with the SNR is the current environment type.

### Claim 11

An electronic device, comprising a voice recognition device, a voice recording device connected to the voice recognition device, and a microphone connected to the voice recording device;
wherein the voice recording device is configured to collect and record an input voice by using the microphone, and is configured to input the recorded input voice to the voice recognition device;
wherein the voice recognition device is configured to:
receive an input voice;
acquire a detection voice and a to-be-recognized voice by dividing the input voice, wherein a length of voice data comprised in the detection voice is less than a length of voice data comprised in the to-be-recognized voice;
select, after comparing the acquired detection voice with a voice training sample under a different sample environment, a sample environment corresponding to a voice training sample that has a minimum difference with the detection voice, as a detection environment type, wherein the sample environment comprises a quiet environment and a noise environment;
detect a storage area in the voice recognition device;
output, when a recognizable previous environment type exists in the storage area, a voice correction instruction according to a result of comparison between the detection environment type and the previous environment type, wherein the previous environment type is a quiet environment or a noise environment;
control, according to the voice correction instruction, correction on the to-be-recognized voice, and output an initial recognition result;
separately compare the received to-be-recognized voice with a voice training sample under a different sample environment, and select sample environment corresponding to a voice training sample that has a minimum difference with the to-be-recognized voice, as a current environment type;
store the current environment type to the storage area, and abandon the current environment type after preset duration; and
output a final recognition result after a confidence value of the initial recognition result is adjusted according to the current environment type.

### Claim 12 (depends on 11)

The electronic device according to claim 11, wherein when the previous environment type is not recognized in the storage area, the voice recording device is further configured to:
acquire a pre-stored initial environment type, wherein the initial environment type comprises a quiet environment or a noise environment;
determine according to the initial environment type and the detection environment type; and
output the voice correction instruction.

### Claim 13 (depends on 12)

The electronic device according to claim 12, wherein the determine according to the initial environment type and the detection environment type, and output the voice correction instruction comprises:
determine whether the initial environment type is the same as the detection environment type;
if the initial environment type is the same as the detection environment type, output a voice correction instruction used for voice quality enhancement when both the initial environment type and the detection environment type are noise environments, and output a voice correction instruction used for disabling noise reduction processing when both the initial environment type and the detection environment type are quiet environments; and
if the initial environment type is not the same as the detection environment type, output a voice correction instruction used for voice quality enhancement when the initial environment type is a noise environment, and output a voice correction instruction used for disabling noise reduction processing when the initial environment type is a quiet environment.

### Claim 14 (depends on 11)

The electronic device according to claim 11, wherein the output, when a recognizable previous environment type exists in the storage area, a voice correction instruction according to a result of comparison between the detection environment type and the previous environment type comprises:
acquire the previous environment type and effective impact duration T of the previous environment type on the input voice;
calculate a time difference t between time for inputting the detection voice and time for previously inputting a voice, and an impact value w(t) of the previous environment type on the detection environment type, wherein w(t) is a truncation function that decays with time t, a value of w(t) is obtained by training sample data of a voice training sample under a different sample environment, and values of t and T are positive integers;
determine a balance relationship between the previous environment type and the detection environment type;
output, when both the previous environment type and the detection environment type are noise environments, a voice correction instruction used for voice quality enhancement;
output, when both the previous environment type and the detection environment type are quiet environments, a voice correction instruction used for disabling noise reduction processing;
output, when the previous environment type is a noise environment, the detection environment type is a quiet environment, and w(t)>=0.5, a voice correction instruction used for voice quality enhancement;
output, when the previous environment type is a noise environment, the detection environment type is a quiet environment, and w(t)<0.5, a voice correction instruction used for disabling noise reduction processing; and
when the w(t)>T, output, when the detection environment type is a quiet environment, a voice correction instruction used for disabling noise reduction processing, and output, when the detection environment is a noise environment, a voice correction instruction used for voice quality enhancement.

### Claim 15 (depends on 11)

The electronic device according to claim 11, wherein the separately compare the received to-be-recognized voice with a voice training sample under a different sample environment, and select a sample environment corresponding to a voice training sample that has a minimum difference with the to-be-recognized voice, as a current environment type comprises:
analyze a voice frame part and a noise frame part of the received to-be-recognized voice to acquire a noise level, a voice level, and a signal-to-noise ratio (SNR) of the to-be-recognized voice;
compare the noise level, the voice level, and the SNR of the to-be-recognized voice with a noise training level, a voice training level, and a training SNR of a voice training sample under a different sample environment, respectively; and
determine that a sample environment corresponding to a noise training level that has a minimum difference with the noise level, a voice training level that has a minimum difference with the voice level, and a training SNR that has a minimum difference with the SNR is the current environment type.

### Claim 16 (depends on 11)

The electronic device according to claim 11, wherein
the preset duration when the current environment type is a quiet environment is longer than the preset duration when the current environment type is a noise environment.

### Claim 17 (depends on 11)

The electronic device according to claim 11, wherein the noise environment comprises: a vehicle-mounted low noise environment, a vehicle-mounted high noise environment, an ordinary roadside environment, a busy roadside environment, and a noisy environment.