System and method for hierarchical voice actived dialling and service selection

• US 20060111914A1
• Filed: 10/20/2003
• Published: 05/25/2006
• Est. Priority Date: 10/18/2002
• Status: Abandoned Application

• Current Assignee: Nederlandse Organisatie Voor Toegepast-Natuurwetenschappelijk Onderzoek Tno
• Original Assignee: Nederlandse Organisatie Voor Toegepast-Natuurwetenschappelijk Onderzoek Tno
• Inventors: van Deventer, Mattijs Oskar
• Application Number:
  US10/531,807
• Publication Number:
  US 20060111914A1
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals

Abstract

The invention is related to an automatic speech recognition system, in particular for use within telecommunications switching systems, providing hierarchically structured set of servers each server being arranged to interpret part of a spoken user request

Claims

1. A speech recognition system being arranged to satisfy a spoken user request comprising a set of servers, at least one of said servers comprising:

means for recognizing part of the spoken user request, arranged to recognize a spoken user request comprising registered sounds;

means for requesting another of said servers to analyze said spoken user request based on partial recognition of said spoken user request;

characterized in that the registered sounds are Sound Names, identifying an entity, and Speech Markers indicating the type of entity.

2. The speech recognition system according to claim 1 wherein said system is arranged as a voice activated dialling and telecommunication service selection system.

3. A voice activated dialling system for satisfying a spoken user request, comprising:

a hierarchically structured set of distributed servers containing databases, each of said databases containing a different set of records providing mappings from a combination of registered Sound Names and Speech Markers to another one of said databases, and records providing mappings from a combination of registered Sound Names and Speech Markers to a telecommunication address of an entity;

means for recognizing part of the spoken user request, facilitated by said mappings;

means for requesting another one of said servers to analyze said spoken user request based on recognition of said part of said spoken user request.

4. The voice activated dialling system according to claim 3, wherein the distributed servers are DNS-type servers.

5. A telecommunication network, comprising the voice dialling system according to claim 3.

6. A method for providing voice dialling services comprising:

storing in a plurality of hierarchically structured distributed databases, records providing mappings from a combination of registered Sound Names and Speech Markers to another one of said databases, and records providing mappings from a combination of registered Sound Names and Speech Markers to a telecommunication address of an entity;

receiving a spoken user request;

recognizing part of the spoken user request, facilitated by said mappings;

requesting another one of said databases to analyze said spoken user request based on recognition of said part of said spoken user request.

7. The method according to claim 6, wherein plurality of hierarchically structured distributed databases are stored in DNS-type servers.

8. A method for registering Sound Names and Speech Markers comprising steps of:

defining domains and subdomains;

delegating authority for defining Sound Names and Speech Markers for a subdomain;

defining and registering the mapping between a combination of Sound Names and Speech Markers and telecommunication addresses.

10. The Sound Name Server (30) according to claim 8, wherein the database comprises Sound Names and Speech Markers, and wherein the speech analyzer analyses the speech input string by using Sound Names and Speech Markers.

9. A Sound Name Server (30) for partially interpreting a speech input string, comprising:

the sound name arranged for receiving a speech input string as user request;

a voice recorder (33) for recording the speech input string;

a database (3 5);

a speech analyzer for recognizing in the speech input using the database at least one of communication address and the identity of a further Sound Name Server, the sound name arranged for receiving at least one of a communication address and an identity of a further Sound Name Server;

the sound name server further arranged for transmitting at least one of a communication address and the identity of a yet a further Sound Name server;

the sound name server further arranged for forwarding a speech recording to yet a further Sound Name Server.

11. A telecommunication network comprising call routing means, whereby the call routing means comprise Sound name Servers according to claim 9.