Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021045955 - SPEECH RECOGNITION SYSTEMS AND METHODS

Publication Number WO/2021/045955
Publication Date 11.03.2021
International Application No. PCT/US2020/048149
International Filing Date 27.08.2020
IPC
G10L 15/22 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
22Procedures used during a speech recognition process, e.g. man-machine dialog
G10L 15/04 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
04Segmentation; Word boundary detection
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 15/14 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 15/183 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
183using context dependencies, e.g. language models
G10L 15/00 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
CPC
G10L 15/063
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
06Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
063Training
G10L 15/183
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
183using context dependencies, e.g. language models
Applicants
  • TELEPATHY LABS, INC. [US]/[US]
Inventors
  • AVIJEET, Vijeta
Agents
  • ABRAMSON, Michael, T.
  • COLANDREO, Brian, J.
  • WHITTENBERGER, Mark, H.
  • DERKASCH, Alexa, Maria, J.
  • PLACKER, Jeffrey, T.
  • SARGEANT, Heath, M.
Priority Data
62/895,79204.09.2019US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SPEECH RECOGNITION SYSTEMS AND METHODS
(FR) SYSTÈMES ET PROCÉDÉS DE RECONNAISSANCE VOCALE
Abstract
(EN)
A speech processing system and a method therefor is provided. The speech processing system may capture one or more speech signals. Each of the one or more speech signals may include at least one dialogue uttered by a user. Dialogues may be extracted from the one or more speech signals. Frequently uttered dialogues may be identified over a period of time. The frequently uttered dialogues may be a set of dialogues that are uttered by the user a number of times during the period of time more than other dialogues uttered by the user during the period of time. A local language model and a local acoustic model may be generated based on, at least in part, the frequently uttered dialogues. The one or more speech signals may be processed based on, at least in part, the local language model and the local acoustic model.
(FR)
La présente invention concerne un système de traitement vocal et un procédé associé. Le système de traitement vocal peut capturer un ou plusieurs signaux vocaux. Chacun desdits signaux vocaux peut comprendre au moins un dialogue prononcé par un utilisateur. Des dialogues peuvent être extraits desdits signaux vocaux. Des dialogues fréquemment prononcés peuvent être identifiés au cours d'une période de temps. Les dialogues fréquemment prononcés peuvent être un ensemble de dialogues qui sont prononcés par l'utilisateur un certain nombre de fois pendant la période de temps plus fréquemment que d'autres dialogues prononcés par l'utilisateur pendant la période de temps. Un modèle de langue local et un modèle acoustique local peuvent être générés sur la base, au moins en partie, des dialogues fréquemment prononcés. Lesdits signaux vocaux peuvent être traités sur la base, au moins en partie, du modèle de langue local et du modèle acoustique local.
Latest bibliographic data on file with the International Bureau