METHOD AND DEVICE FOR VOICEPRINT RECOGNITION

• US 20160358610A1
• Filed: 08/18/2016
• Published: 12/08/2016
• Est. Priority Date: 01/28/2013
• Status: Active Grant

• Current Assignee: Tencent Technology Shenzhen Company Limited (Tencent Holdings Limited)
• Original Assignee: Tencent Technology Shenzhen Company Limited (Tencent Holdings Limited)
• Inventors: WANG, Eryu, LU, Li, ZHANG, Xiang, LIU, Haibo, LI, Lou, RAO, Feng, LU, Duling, YUE, Shuai, CHEN, Bo
• Granted Patent: US 9,940,935 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 17/02 Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
• CPC Class Codes: G10L 17/04 Training, enrolment or model building
• CPC Class Codes: G10L 17/08 Use of distortion metrics or a particular distance between probe pattern and reference templates
• CPC Class Codes: G10L 17/18 Artificial neural networks; Connectionist approaches

Abstract

A method is performed at a device having one or more processors and memory. The device establishes a first-level Deep Neural Network (DNN) model based on unlabeled speech data, the unlabeled speech data containing no speaker labels and the first-level DNN model specifying a plurality of basic voiceprint features for the unlabeled speech data. The device establishes a second-level DNN model by tuning the first-level DNN model based on labeled speech data, the labeled speech data containing speech samples with respective speaker labels, wherein the second-level DNN model specifies a plurality of high-level voiceprint features. Using the second-level DNN model, registers a first high-level voiceprint feature sequence for a user based on a registration speech sample received from the user. The device performs speaker verification for the user based on the first high-level voiceprint feature sequence registered for the user.

Claims

1. A method, comprising:

at a device having one or more processors and memory;

establishing a first-level Deep Neural Network (DNN) model based on unlabeled speech data, the unlabeled speech data containing no speaker labels and the first-level DNN model specifying a plurality of basic voiceprint features for the unlabeled speech data;

establishing a second-level DNN model by tuning the first-level DNN model based on labeled speech data, the labeled speech data containing speech samples with respective speaker labels, wherein the second-level DNN model specifies a plurality of high-level voiceprint features;

using the second-level DNN model, registering a first high-level voiceprint feature sequence for a user based on a registration speech sample received from the user; and

performing speaker verification for the user based on the first high-level voiceprint feature sequence registered for the user.

2. The method of claim 1, wherein establishing the second-level DNN model by tuning the first-level DNN model based on labeled speech data comprises:

imposing at least two constraints on the second-level DNN model, including;

(1) distances between characteristic voiceprints generated from speech samples of different speakers increase with training, and (2) distances between characteristic voiceprints generated from speech samples of the same speaker decrease with training.

3. The method of claim 1, wherein establishing the second-level DNN model by tuning the first-level DNN model based on labeled speech data comprises:

applying sparse coding limit rules to train the first-level DNN model based on the labeled speech data.

4. The method of claim 1, wherein establishing the second-level DNN model by tuning the first-level DNN model based on labeled speech data comprises:

applying maximum cross entropy rules to train the first-level DNN model based on the labeled speech data.

5. The method of claim 1, wherein registering the first high-level voiceprint feature sequence for the user based on the registration speech sample received from the user comprises:

obtaining a basic voiceprint feature sequence for the user from the registration speech sample based on the first-level DNN model; and

providing the basic voiceprint feature sequence for the user as input to the second-level DNN model to obtain the first high-level voiceprint feature sequence for the user.

6. The method of claim 1, wherein performing the speaker verification for the user based on the first high-level voiceprint feature sequence registered for the user comprises:

receiving, from the user, a test speech sample;

obtaining a second high-level voiceprint feature sequence based on the test speech sample using the first-level DNN model and the second-level DNN model in sequence;

determining a distance between the second high-level voiceprint feature sequence and the first high-level voiceprint feature sequence registered for the user; and

in accordance with a determination that the distance between the second high-level voiceprint feature sequence and the first high-level voiceprint feature sequence is less than a preset threshold, automatically, without user intervention, verifying the identity of the user.

7. The method of claim 6, wherein determining the distance between the second high-level voiceprint feature sequence and the first high-level voiceprint feature sequence registered for the user comprises:

determining a Euclidean distance between respective Gaussian models of the second high-level voiceprint feature sequence obtained from the test speech sample and the first high-level voiceprint feature sequence registered for the user.

8. A voiceprint recognition system, comprising:

one or more processors; and

memory storing instructions that, when executed by the one or more processors, cause the processors to perform operations comprising;

establishing a first-level Deep Neural Network (DNN) model based on unlabeled speech data, the unlabeled speech data containing no speaker labels and the first-level DNN model specifying a plurality of basic voiceprint features for the unlabeled speech data;

establishing a second-level DNN model by tuning the first-level DNN model based on labeled speech data, the labeled speech data containing speech samples with respective speaker labels, wherein the second-level DNN model specifies a plurality of high-level voiceprint features;

using the second-level DNN model, registering a first high-level voiceprint feature sequence for a user based on a registration speech sample received from the user; and

performing speaker verification for the user based on the first high-level voiceprint feature sequence registered for the user.

9. The system of claim 8, wherein establishing the second-level DNN model by tuning the first-level DNN model based on labeled speech data comprises:

imposing at least two constraints on the second-level DNN model, including;

(1) distances between characteristic voiceprints generated from speech samples of different speakers increase with training, and (2) distances between characteristic voiceprints generated from speech samples of the same speaker decrease with training.

10. The system of claim 8, wherein establishing the second-level DNN model by tuning the first-level DNN model based on labeled speech data comprises:

applying sparse coding limit rules to train the first-level DNN model based on the labeled speech data.

11. The system of claim 8, wherein establishing the second-level DNN model by tuning the first-level DNN model based on labeled speech data comprises:

applying maximum cross entropy rules to train the first-level DNN model based on the labeled speech data.

12. The system of claim 8, wherein registering the first high-level voiceprint feature sequence for the user based on the registration speech sample received from the user comprises:

obtaining a basic voiceprint feature sequence for the user from the registration speech sample based on the first-level DNN model; and

providing the basic voiceprint feature sequence for the user as input to the second-level DNN model to obtain the first high-level voiceprint feature sequence for the user.

13. The system of claim 8, wherein performing the speaker verification for the user based on the first high-level voiceprint feature sequence registered for the user comprises:

receiving, from the user, a test speech sample;

obtaining a second high-level voiceprint feature sequence based on the test speech sample using the first-level DNN model and the second-level DNN model in sequence;

determining a distance between the second high-level voiceprint feature sequence and the first high-level voiceprint feature sequence registered for the user; and

in accordance with a determination that the distance between the second high-level voiceprint feature sequence and the first high-level voiceprint feature sequence is less than a preset threshold, automatically, without user intervention, verifying the identity of the user.

14. The system of claim 13, wherein determining the distance between the second high-level voiceprint feature sequence and the first high-level voiceprint feature sequence registered for the user comprises:

determining a Euclidean distance between respective Gaussian models of the second high-level voiceprint feature sequence obtained from the test speech sample and the first high-level voiceprint feature sequence registered for the user.

15. A non-transitory computer-readable medium storing instructions that, when executed by a computer system with one or more processors, cause the processors to perform operations comprising:

establishing a first-level Deep Neural Network (DNN) model based on unlabeled speech data, the unlabeled speech data containing no speaker labels and the first-level DNN model specifying a plurality of basic voiceprint features for the unlabeled speech data;

establishing a second-level DNN model by tuning the first-level DNN model based on labeled speech data, the labeled speech data containing speech samples with respective speaker labels, wherein the second-level DNN model specifies a plurality of high-level voiceprint features;

using the second-level DNN model, registering a first high-level voiceprint feature sequence for a user based on a registration speech sample received from the user; and

performing speaker verification for the user based on the first high-level voiceprint feature sequence registered for the user.

16. The computer-readable medium of claim 15, wherein establishing the second-level DNN model by tuning the first-level DNN model based on labeled speech data comprises:

imposing at least two constraints on the second-level DNN model, including;

(1) distances between characteristic voiceprints generated from speech samples of different speakers increase with training, and (2) distances between characteristic voiceprints generated from speech samples of the same speaker decrease with training.

17. The computer-readable medium of claim 15, wherein establishing the second-level DNN model by tuning the first-level DNN model based on labeled speech data comprises:

applying sparse coding limit rules to train the first-level DNN model based on the labeled speech data.

18. The computer-readable medium of claim 15, wherein establishing the second-level DNN model by tuning the first-level DNN model based on labeled speech data comprises:

applying maximum cross entropy rules to train the first-level DNN model based on the labeled speech data.

19. The computer-readable medium of claim 15, wherein registering the first high-level voiceprint feature sequence for the user based on the registration speech sample received from the user comprises:

obtaining a basic voiceprint feature sequence for the user from the registration speech sample based on the first-level DNN model; and

providing the basic voiceprint feature sequence for the user as input to the second-level DNN model to obtain the first high-level voiceprint feature sequence for the user.

20. The computer-readable medium of claim 15, wherein performing the speaker verification for the user based on the first high-level voiceprint feature sequence registered for the user comprises:

receiving, from the user, a test speech sample;

obtaining a second high-level voiceprint feature sequence based on the test speech sample using the first-level DNN model and the second-level DNN model in sequence;

determining a distance between the second high-level voiceprint feature sequence and the first high-level voiceprint feature sequence registered for the user; and

in accordance with a determination that the distance between the second high-level voiceprint feature sequence and the first high-level voiceprint feature sequence is less than a preset threshold, automatically, without user intervention, verifying the identity of the user.