SPEAKER ENROLLMENT

Patent №

US 10,839,810

Granted

2020-11-17

Filed 2018

Owner

CIRRUS LOGIC INTERNATIONAL SEMICONDUCTOR LTD.

+1 more

Lab

AI components

3

ml · nlp · speech

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16192914

A method of speaker modelling for a speaker recognition system, comprises: receiving a signal comprising a speaker's speech; and, for a plurality of frames of the signal: obtaining a spectrum of the speaker's speech; generating at least one modified spectrum, by applying effects related to a respective vocal effort; and extracting features from the spectrum of the speaker's speech and the at least one modified spectrum. The method further comprises forming at least one speech model based on the extracted features.

Machine learningNatural languageSpeechG10L 17/04G10L 17/00G10L 17/02G10L 17/20G10L 2021/03646

AI classification

Speech1.00
Natural language1.00
Machine learning1.00
Vision0.45
Evolutionary computation0.00
Planning0.00
Knowledge representation0.00
AI hardware0.00

Ownership

CIRRUS LOGIC INTERNATIONAL SEMICONDUCTOR LTD.

assignment · 475210660

CIRRUS LOGIC, INC.

assignment · 537300089

Assignors

CIRRUS LOGIC INTERNATIONAL SEMICONDUCTOR LTD.

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC