Processing

Please wait...

Settings

Settings

Goto Application

1. WO1998016048 - VOICE-DIALING SYSTEM USING MODEL OF CALLING BEHAVIOR

Publication Number WO/1998/016048
Publication Date 16.04.1998
International Application No. PCT/US1997/017623
International Filing Date 06.10.1997
Chapter 2 Demand Filed 04.05.1998
IPC
G10L 15/18 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
18using natural language modelling
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
H04M 1/27 2006.01
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
MTELEPHONIC COMMUNICATION
1Substation equipment, e.g. for use by subscribers
26Devices for calling a subscriber
27Devices whereby a plurality of signals may be stored simultaneously
H04M 3/22 2006.01
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
MTELEPHONIC COMMUNICATION
3Automatic or semi-automatic exchanges
22Arrangements for supervision, monitoring or testing
H04M 3/42 2006.01
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
MTELEPHONIC COMMUNICATION
3Automatic or semi-automatic exchanges
42Systems providing special services or facilities to subscribers
H04M 3/493 2006.01
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
MTELEPHONIC COMMUNICATION
3Automatic or semi-automatic exchanges
42Systems providing special services or facilities to subscribers
487Arrangements for providing information services, e.g. recorded voice services or time announcements
493Interactive information services, e.g. directory enquiries
CPC
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
G10L 15/22
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 dialogue
H04M 1/271
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
MTELEPHONIC COMMUNICATION
1Substation equipment, e.g. for use by subscribers; Analogous equipment at exchanges
26Devices for signalling identity of wanted subscriber
27Devices whereby a plurality of signals may be stored simultaneously
271controlled by voice recognition
H04M 3/2218
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
MTELEPHONIC COMMUNICATION
3Automatic or semi-automatic exchanges
22Supervisory, monitoring, ; management, i.e. operation, administration, maintenance; or testing arrangements
2218Call detail recording
H04M 3/42204
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
MTELEPHONIC COMMUNICATION
3Automatic or semi-automatic exchanges
42Systems providing special services or facilities to subscribers
42204Arrangements at the exchange for service or number selection by voice
H04M 3/42229
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
MTELEPHONIC COMMUNICATION
3Automatic or semi-automatic exchanges
42Systems providing special services or facilities to subscribers
42229Personal communication services, i.e. services related to one subscriber independent of his terminal and/or location
Applicants
  • NORTHERN TELECOM LIMITED [CA]/[CA]
Inventors
  • WILL, Craig, Alexander
Agents
  • GARRETT, Arthur, S.
Priority Data
08/726,60407.10.1996US
08/942,20101.10.1997US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) VOICE-DIALING SYSTEM USING MODEL OF CALLING BEHAVIOR
(FR) SYSTEME DE COMPOSITION EN VOCAL A L'AIDE D'UN MODELE DE COMPORTEMENT D'APPEL
Abstract
(EN)
A method and apparatus for assisting voice-dialing using a model of an individual's calling behavior to improve recognition of an input name corresponding to a desired telephone number. When the individual picks up a telephone, activity is initiated in a neural network model of the individual's calling behavior that predicts the likelihood that different numbers will be called, given such predictors as the day of the week and the time of day. The model is constructed by training the neural network with data from the user's history of making and receiving telephone calls. The auditory output from an automatic speech recognition system and the output from the user model are integrated together so as to select the number that is most likely to be the number desired by the speaker. The system can also provide automatic directory assistance, by speaking the number aloud rather than dialing it. In one version, the system is a personal directory for an individual maintained on that individual's personal computer. In another version, the system serves as a directory for a given physical or virtual site, with information about the institutional organization at the site in addition to individual calling histories used to track calling patterns and make predictions about the likelihood of calls within the site.
(FR)
Procédé et appareil d'assistance de composition en vocal utilisant un modèle de comportement d'appel d'un individu qui permet d'améliorer le système de reconnaissance d'un nom introduit vocalement correspondant à un numéro de téléphone désiré. Lorsque la personne décroche le combiné, une activité est déclenchée dans un modèle neuromimétique du comportement d'appel de la personne, ce modèle neuromimétique prévoyant que différents numéros seront vraisemblablement appelés, et donnant des valeurs prédictives telles que le jour de la semaine et l'heure du jour. On construit le modèle en entraînant l'ordinateur neuromimétique avec les données issues de l'historique d'envoi et de réception d'appels de l'utilisateur. La sortie auditive d'un système de reconnaissance vocale automatique et la sortie du modèle utilisateur sont intégrées de façon à sélectionner le numéro qui doit être très probablement le numéro désiré par le locuteur. Le système peut également assurer une assistance-annuaire automatique en prononçant le numéro à haute voix plutôt qu'en le composant. Selon une version de l'invention, le système représente un annuaire personnel d'un individu, maintenu sur cet ordinateur personnel. Selon une autre version, le système sert d'annuaire pour un site physique ou virtuel donné, des informations, concernant l'organisation institutionnelle du site ajoutées à des historiques d'appels d'individus, étant utilisées pour suivre des modes d'appels et établir des prévisions d'appels vraisemblables dans le site.
Also published as
Latest bibliographic data on file with the International Bureau