METHOD FOR AUTOMATIC SOUND SYNTHESIS

Patent №

US 5,900,568

Granted

1999-05-04

Filed 1998

Owner

IBM CORPORATION

AI components

2

ml · speech

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

09080323

A method for automatically adjusting the parameters of a synthesizer includes generating a first synthesized signal based on an initial set of synthesizer parameters, comparing the first synthesized signal to an input sound signal, and generating a control signal for adjusting a subset of parameters of the synthesizer to minimize the differences between the first synthesized signal and the input sound signal. These steps may be iteratively performed for a predetermined number of additional subsets of synthesizer parameters, until a final output of the synthesizer is obtained which represents an optimization of the synthesis of the input sound signal.

Machine learningSpeechG10H 7/00G10H 2250/351G10H 2250/411G10H 2250/421G10H 2250/431G10H 2250/641

AI classification

Speech1.00
Machine learning0.53
Evolutionary computation0.48
AI hardware0.45
Planning0.11
Vision0.01
Knowledge representation0.01
Natural language0.01

Ownership

IBM CORPORATION

assignment · 92160748

Assignors

ABRAMS, STEVEN R.

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

© 2026 NYSGPT2525 LLC