METHOD FOR CONDITIONING A DIGITAL SPEECH SIGNAL

Patent №

US 6,775,650

Granted

2004-08-10

Filed 2000

Owner

MATRA NORTEL COMMUNICATIONS

+1 more

Lab

AI components

2

nlp · speech

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

09509146

The invention concerns a method for conditioning a digital speech signal(s) processed by successive frames, which consists carrying out a harmonic analysis to estimate the pitch on each frame where it has a speech activity, and in oversampling at an oversampling frequency (fe) which is a multiple of the estimated pitch.

Natural languageSpeechG10L 21/0364G10L 19/0212G10L 21/0232G10L 25/78G10L 25/93

AI classification

Speech1.00
Natural language1.00
Machine learning0.00
Vision0.00
Evolutionary computation0.00
Planning0.00
AI hardware0.00
Knowledge representation0.00

Ownership

MATRA NORTEL COMMUNICATIONS

assignment · 108460609

APPLE INC.

assignment · 286670252

Assignors

LOCKWOOD, PHILIP, LUBIARZ, STEPHANE

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

© 2026 NYSGPT2525 LLC