Search International and National Patent Collections
Some content of this application is unavailable at the moment.
If this situation persists, please contact us atFeedback&Contact
1. (WO1991017417) AUDIO-AUGMENTED DATA KEYING
Latest bibliographic data on file with the International Bureau

Pub. No.: WO/1991/017417 International Application No.: PCT/US1991/002774
Publication Date: 14.11.1991 International Filing Date: 23.04.1991
Chapter 2 Demand Filed: 05.11.1991
IPC:
G10L 15/22 (2006.01) ,G10L 15/24 (2006.01) ,H04M 11/06 (2006.01)
G PHYSICS
10
MUSICAL INSTRUMENTS; ACOUSTICS
L
SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15
Speech recognition
22
Procedures used during a speech recognition process, e.g. man-machine dialog
G PHYSICS
10
MUSICAL INSTRUMENTS; ACOUSTICS
L
SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15
Speech recognition
24
Speech recognition using non-acoustical features
H ELECTRICITY
04
ELECTRIC COMMUNICATION TECHNIQUE
M
TELEPHONIC COMMUNICATION
11
Telephonic communication systems specially adapted for combination with other electrical systems
06
Simultaneous speech and data transmission, e.g. telegraphic transmission over the same conductors
Applicants:
ROTH, Richard, G. [US/US]; US
Inventors:
ROTH, Richard, G.; US
Agent:
MAUNE, James, J. ; Brumbaugh, Graves, Donohue & Raymond 30 Rockefeller Plaza New York, NY 10112, US
Priority Data:
521,53710.05.1990US
Title (EN) AUDIO-AUGMENTED DATA KEYING
(FR) INTRODUCTION DE DONNEES A L'AIDE D'UN CLAVIER ET D'UNE EMISSION VOCALE
Abstract:
(EN) Present-day limitations of the conventional touch-tone keypad are overcome permitting alphabetic information to be entered into a distant computer. The caller speaks a speech portion into a telephone handset, and then types out the speech portion on the touch-tone keypad. The computer receiving the call converts the spoken voice information into a form suitable for additional digital processing, as by extracting speech-recognition features from the spoken information (32). The computer processes the typed numeric string into a list of all the possible combinations of characters it could represent (31). The extent of correlation between the features of the spoken speech portion and each of the combinations is determined (33), and the combination having the highest correlation is taken to be the speech portion entered by the user (34).
(FR) La présente invention surmonte les limitations actuelles du clavier à touches conventionnel et permet d'entrer des informations alphabétiques dans un ordinateur situé à distance. L'appelant prononce une portion de phrase dans un combiné téléphonique et tape ensuite ladite portion de phrase sur le clavier à touches. L'ordinateur recevant l'appel convertit l'information vocale parlée en une forme qui convient à un traitement numérique supplémentaire, en extrayant de l'information parlée des caractéristiques d'identification des paroles prononcées (32). L'ordinateur transforme la suite numérique tapée en une liste de toutes les combinaisons possibles de caractères qu'elle pourrait représenter (31). L'ampleur de la corrélation entre les caractéristiques de la portion de phrase parlée et chacune des combinaisons est déterminée (33) et la combinaison présentant la corrélation la plus élevée est considérée comme étant la portion de phrase entrée par l'utilisateur (34).
Designated States: AU, BG, BR, CA, FI, HU, JP, KR, NO, RO, SU
European Patent Office (AT, BE, CH, DE, DK, ES, FR, GB, GR, IT, LU, NL, SE)
Publication Language: English (EN)
Filing Language: English (EN)
Also published as:
CA2081904AU1991078783