Voice registration method and system, and voice recognition method and system based on voice registration method and system
US7502736B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 6, 2001 |
| Grant date | Mar 10, 2009 |
| Priority date | — |
| Expiry date | Jul 1, 2024 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/063
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Disclosed is a voice registration method for voice recognition, comprising the steps of analyzing a spectrum of a sound signal inputted from the outside; extracting predetermined language units for a speaker recognition from a voice signal in the sound signal; measuring the loudness of each language unit; collecting voice data on registered (background) speakers including loudness data of the plurality of background speakers as a reference onto voice database; determining whether the loudness of each language unit is within a predetermined loudness range based on the voice data base; learning each language unit by using a multi-layer perceptron in the case that at least a predetermined number of language units are within the predetermined loudness range; and storing data on the learned language unit as data for recognizing the speaker. With this configuration, loudness of a speaker is considered at learning for registering his/her voice and at verifying a speaker.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.