Granted Patent B2

US 12,380,895 · App. 17/543,980 · Granted Aug 5, 2025

Inventor: John Paul Lesso (Edinburgh, GB)

Assignee: Cirrus Logic Inc.

G10L17/22G10L17/00G10L17/02G10L17/06G10L25/48G10L25/51G10L25/84G10L25/18G10L25/30G10L25/93

Abstract

Claims (35)

1. A method of analysis of an audio signal, the method comprising:

receiving an audio signal representing speech of an enrolled user;

extracting first and second components of the audio signal, the first component comprising first features exclusively representing a first acoustic classes of the speech, the second component comprising second features exclusively representing a second acoustic class of the speech, the first acoustic class of speech being different to the second acoustic class of speech;

analysing the extracted first component of the audio signal with a first model of speech of an enrolled user in the first acoustic class and the extracted second component of the audio signal with a second model of speech of the enrolled user in the second acoustic class, wherein analysing the first and second components of the audio signal with the first and second models of the speech of the enrolled user comprises comparing magnitudes of the first and second components at a number of predetermined frequencies with magnitudes in the first and second models at the number of predetermined frequencies;

based on said comparison, determining a frequency spectrum of a multiplicative disturbance component affecting the first and second components of said audio signal or a frequency spectrum of an additive disturbance component affecting the first and second components of said audio signal; and

compensating the received audio signal for the frequency spectrum of the multiplicative disturbance component or the additive disturbance component to obtain a compensated received audio signal.

2. A method according to claim 1 , wherein the first and second acoustic classes are phonetically distinguishable acoustic classes of speech.

3. A method according to claim 1 , wherein the first and second acoustic classes each comprise one of the following classes:

a) a phoneme class;

b) a vowel class;

c) a fricative class;

d) a sibilant class;

e) a voiced class;

f) an unvoiced class.

4. A method according to claim 1 , wherein extracting first and second components of the audio signal comprises:

identifying periods when the audio signal contains voiced speech; and

identifying remaining periods of speech as containing unvoiced speech.

5. A method according to claim 1 , comprising:

performing a speaker identification process on the received audio signal to form a provisional decision on an identity of a speaker;

selecting the first and second models of the speech of the enrolled user, from a plurality of models, based on the provisional decision on the identity of the speaker; and

performing a second speaker identification process on the compensated received audio signal to form a final decision on the identity of the speaker.

6. A method according to claim 5 , wherein compensating the received audio signal comprises:

identifying at least one part of a frequency spectrum of the received audio signal where a noise level exceeds a threshold level; and

ignoring the identified part of the frequency spectrum of the received audio signal when performing the second speaker identification process.

7. A method according to claim 1 , wherein the first and second acoustic classes of the speech comprise voiced speech and unvoiced speech.

8. A method according to claim 1 , wherein the first and second acoustic classes of the speech comprise first and second phoneme classes.

9. A method according to claim 1 , wherein the first and second acoustic classes of the speech comprise first and second fricatives.

10. A method according to claim 1 , wherein the first and second acoustic classes of the speech comprise fricatives and sibilants.

11. A system for analysis of an audio signal, the system comprising an input for receiving an audio signal, and being configured for:

receiving an audio signal representing speech of an enrolled user;

extracting first and second components of the audio signal, the first component comprising first features exclusively representing a first acoustic classes of the speech, the second component comprising second features exclusively representing a second acoustic class of the speech, the first acoustic class of speech being different to the second acoustic class of speech;

analysing the extracted first component of the audio signal with a first model of speech of an enrolled user in the first acoustic class and the extracted second component of the audio signal with a second model of speech of the enrolled user in the second acoustic class, wherein analysing the first and second components of the audio signal with the first and second models of the speech of the enrolled user comprises comparing magnitudes of the first and second components at a number of predetermined frequencies with magnitudes in the first and second models at the number of predetermined frequencies;

based on said comparison, determining a frequency spectrum of a multiplicative disturbance component affecting the first and second components of said audio signal or an additive disturbance component affecting the first and second components of said audio signal; and

compensating the received audio signal for the frequency spectrum of the multiplicative disturbance component or the additive disturbance component.

12. A non-transitory computer readable storage medium having computer-executable instructions stored thereon that, when executed by processor circuitry, cause the processor circuitry to perform a method according to claim 1 .

Assignments (2)

Priority Claims (1)

Continuity (3)

References Cited (400)