Processing

Please wait...

Settings

Settings

Goto Application

1. WO1997029482 - SPEECH CODING, RECONSTRUCTION AND RECOGNITION USING ACOUSTICS AND ELECTROMAGNETIC WAVES

Publication Number WO/1997/029482
Publication Date 14.08.1997
International Application No. PCT/US1997/001490
International Filing Date 28.01.1997
Chapter 2 Demand Filed 19.08.1997
IPC
G10L 15/02 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
02Feature extraction for speech recognition; Selection of recognition unit
G10L 15/24 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
24Speech recognition using non-acoustical features
G10L 19/00 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
19Speech or audio signal analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
CPC
G01N 2291/02491
GPHYSICS
01MEASURING; TESTING
NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
2291Indexing codes associated with group G01N29/00
02Indexing codes associated with the analysed material
024Mixtures
02491Materials with nonlinear acoustic properties
G01N 2291/02836
GPHYSICS
01MEASURING; TESTING
NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
2291Indexing codes associated with group G01N29/00
02Indexing codes associated with the analysed material
028Material parameters
02836Flow rate, liquid level
G01N 2291/02872
GPHYSICS
01MEASURING; TESTING
NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
2291Indexing codes associated with group G01N29/00
02Indexing codes associated with the analysed material
028Material parameters
02872Pressure
G06Q 20/204
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
20Payment architectures, schemes or protocols
08Payment architectures
20Point-of-sale [POS] network systems
204comprising interface for record bearing medium or carrier for electronic funds transfer or payment credit
G10L 15/02
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
02Feature extraction for speech recognition; Selection of recognition unit
G10L 15/24
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
24Speech recognition using non-acoustical features
Applicants
  • THE REGENTS OF THE UNIVERSITY OF CALIFORNIA [US]/[US]
Inventors
  • HOLZRICHTER, John, F.
  • NG, Lawrence, C.
Agents
  • SARTORIO, Henry, P.
Priority Data
08/597,58906.02.1996US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SPEECH CODING, RECONSTRUCTION AND RECOGNITION USING ACOUSTICS AND ELECTROMAGNETIC WAVES
(FR) CODAGE, RECONSTITUTION ET RECONNAISSANCE DE LA VOIX A L'AIDE D'ONDES SONORES ET ELECTROMAGNETIQUES
Abstract
(EN)
The use of EM radiation in conjunction with simultaneously recorded speech information enables a complete mathematical coding of acoustic speech. The methods include the forming of a feature vector (12, 13) for each pitch period of voiced speech and the forming of feature vectors (12, 13) for each time frame of unvoiced, as well as for combined voiced and unvoiced speech. The methods include how to deconvolve the speech excitation function from the acoustic speech output to describe the transfer function (7) each time frame. The formation of feature vectors (12, 13) defining all acoustic speech units over well-defined time frames can be used for purposes of speech coding, speech compression, speaker identification, language-of-speech identification, speech recognition, speech synthesis, speech translation, speech telephony, and speech teaching.
(FR)
L'utilisation simultanée d'ondes électromagnétique et de signaux vocaux acoustiques enregistrés permet un codage mathématique complet de la parole. Le procédé consiste à créer un vecteur de caractérisation (12, 13) pour chaque tranche de temps sonore et un vecteur de caractérisation pour chaque tranche de temps non sonore, de même que pour les tranche de temps sonores et non sonores combinées. Il comporte également un moyen de déconvolution de la fonction d'excitation des émissions sonores afin de décrire la fonction de transfert (7) correspondant à chacune des tranche de temps. La formation des vecteurs de caractérisation (12, 13) définissant chacun des phonèmes pendant des tranche de temps bien définies peut servir au codage de la parole, à la compression de la parole, à l'identification d'un locuteur, à l'identification de la langue parlée, à la reconnaissance de la voix, à la synthèse vocale, aux traductions, à la téléphonie, et à l'enseignement de la parole.
Also published as
Latest bibliographic data on file with the International Bureau