Processing

Please wait...

Settings

Settings

1. WO2000043989 - SELECTING A TARGET SEQUENCE OF WORDS THAT CORRESPONDS TO AN UTTERANCE

Publication Number WO/2000/043989
Publication Date 27.07.2000
International Application No. PCT/US2000/001426
International Filing Date 20.01.2000
Chapter 2 Demand Filed 18.08.2000
IPC
G10L 15/14 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
08Speech classification or search
14using statistical models, e.g. Hidden Markov Models
G10L 15/18 2013.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
08Speech classification or search
18using natural language modelling
CPC
G10L 15/142
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
08Speech classification or search
14using statistical models, e.g. Hidden Markov Models [HMMs]
142Hidden Markov Models [HMMs]
G10L 15/1815
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
08Speech classification or search
18using natural language modelling
1815Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
Applicants
  • DRAGON SYSTEMS, INC. [US/US]; 320 Nevada Street Newton, MA 02160, US (AllExceptUS)
  • BAKER, James, K. [US/US]; US (UsOnly)
  • BASYE, Kenneth, J. [US/US]; US (UsOnly)
  • BAMBERG, Paul, G. [US/US]; US (UsOnly)
Inventors
  • BAKER, James, K.; US
  • BASYE, Kenneth, J.; US
  • BAMBERG, Paul, G.; US
Agents
  • FEIGENBAUM, David, L.; Fish & Richardson P.C. 225 Franklin Street Boston, MA 02110-2804, US
  • HAYDEN, John, F.; Fish & Richardson, P.C. 601 Thirteenth Street, NW Washington, D.C. 20005 , US
Priority Data
09/316,19121.05.1999US
60/116,60421.01.1999US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SELECTING A TARGET SEQUENCE OF WORDS THAT CORRESPONDS TO AN UTTERANCE
(FR) SELECTION D'UNE SEQUENCE DE MOTS CIBLE CORRESPONDANT A UN ENONCE
Abstract
(EN)
Methods and computer programs for selecting a target (220) that corresponds to an utterance (200). The selecting being performed by acquiring targets and receiving speech recognition output (210) based on an utterance. A target is selected based on the words of the speech recognition output and the words of the targets, the selected target (225) having a different word sequence than the speech recognition output.
(FR)
L'invention concerne des procédés et des programmes informatiques permettant de sélectionner une cible (200) correspondant à un énoncé (200), cette sélection s'effectuant grâce à l'acquisition de cibles et à la réception d'une sortie (210) de reconnaissance de la parole sur la base d'un énoncé. On sélectionne une cible en fonction des mots composant cette sortie de reconnaissance de la parole et des mots composant les différentes cibles, la cible (225) sélectionnée présentant une séquence de mots différente de la sortie de reconnaissance de la parole.
Also published as
Latest bibliographic data on file with the International Bureau