Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020101789 - CONTEXTUAL DENORMALIZATION FOR AUTOMATIC SPEECH RECOGNITION

Publication Number WO/2020/101789
Publication Date 22.05.2020
International Application No. PCT/US2019/049401
International Filing Date 03.09.2019
IPC
G10L 15/26 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
26Speech to text systems
G06F 17/28 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
17Digital computing or data processing equipment or methods, specially adapted for specific functions
20Handling natural language data
28Processing or translating of natural language
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
G06F 17/24 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
17Digital computing or data processing equipment or methods, specially adapted for specific functions
20Handling natural language data
21Text processing
24Editing, e.g. insert/delete
G06F 17/27 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
17Digital computing or data processing equipment or methods, specially adapted for specific functions
20Handling natural language data
27Automatic analysis, e.g. parsing, orthograph correction
G06F 17/22 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
17Digital computing or data processing equipment or methods, specially adapted for specific functions
20Handling natural language data
21Text processing
22Manipulating or registering by use of codes, e.g. in sequence of text characters
Applicants
  • GOOGLE LLC [US]/[US]
Inventors
  • MICHAELY, Assaf, Hurwitz
  • ALEKSIC, Petar
  • MORENO, Pedro
Agents
  • KRUEGER, Brett, A.
Priority Data
16/192,95316.11.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) CONTEXTUAL DENORMALIZATION FOR AUTOMATIC SPEECH RECOGNITION
(FR) DÉNORMALISATION CONTEXTUELLE POUR UNE RECONNAISSANCE VOCALE AUTOMATIQUE
Abstract
(EN)
A method (600) includes receiving a speech input (104) from a user and obtaining context metadata (110) associated with the speech input. The method also includes generating a raw speech recognition result (312) corresponding to the speech input and selecting a list of one or more denormalizers (352) to apply to the generated raw speech recognition result based on the context metadata associated with the speech input. The generated raw speech recognition result includes normalized text. The method also includes denormalizing the generated raw speech recognition result into denormalized text (322) by applying the list of the one or more denormalizers in sequence to the generated raw speech recognition result.
(FR)
La présente invention concerne un procédé (600) comprenant les étapes consistant à recevoir une entrée vocale (104) d'un utilisateur et à obtenir des métadonnées de contexte (110) associées à l'entrée vocale. Le procédé comprend également les étapes consistant à générer un résultat de reconnaissance vocale brut (312) correspondant à l'entrée vocale et à sélectionner une liste d'un ou de plusieurs dénormaliseurs (352) à appliquer au résultat de reconnaissance vocale brut généré sur la base des métadonnées de contexte associées à l'entrée vocale. Le résultat de reconnaissance vocale brut généré comprend un texte normalisé. Le procédé comprend également les étapes consistant à dénormaliser le résultat de reconnaissance vocale brut généré en un texte dénormalisé (322) en appliquant la liste du ou des dénormaliseurs en séquence au résultat de reconnaissance vocale brut généré.
Latest bibliographic data on file with the International Bureau