EP0141497A1
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Voice recognition
Assignee: Domain Dynamics Ltd
•
Filing: 1984-08-22
•
Granted: —
•
Expires: 2004-08-22
Abstract
Abstract An automatic voice recognition system uses time encoded speech format. This has previously only been proposed for digital speech transmission.
Inventors
- 👤 Reginald Alfred King
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-10-30 18:15
CPC Classifications
G; G10; G10L; G10L15/00; G10L15/08; G10L25/00; G10L19/00
Claims Analysis
Total Claims: 14
Claim 1
Independent Claim
13 words
A method of recognising voice signals characterised by utilising Time Encoded Speech (TES).
Claim 2
Independent Claim
13 words
A method of recognising voice signals characterised by utilising Time Encoded Speech (TES).
Claim 3
Dependent Claim
17 words
A method as claimed in claim 1 characterised by utilising Time Encoded Speech (TES) symbol event desriptors.
Claim 4
Dependent Claim
58 words
A voice recognition system, characterised in that voice signals are encoded in a TES format, and that the relationships between at least some of the parameters comprising the TES symbol stream and a test signal (or signals) are examined to provide an output signal indicative of the nature of the voice signal as a result of the examination.
Claim 5
Dependent Claim
58 words
A voice recognition system, characterised in that voice signals are encoded in a TES format, and that the relationships between at least some of the parameters comprising the TES symbol stream and a test signal (or signals) are examined to provide an output signal indicative of the nature of the voice signal as a result of the examination.
Claim 6
Dependent Claim
40 words
A voice recognition system as claimed in claim 3, characterised in that the parameters include events comprising the symbol stream and/or the structure of the symbol stream and/or the location occupied, trajectory followed or movement occurring of the symbol stream.
Claim 7
Dependent Claim
29 words
A voice recognition system as claimed in claim 3, characterised in that the test signal is a test voice signal or a stylised or artificial version of that signal.
Claim 8
Dependent Claim
31 words
A system as claimed in claim 3, characterised in that numerical descriptions of the or each parameter are derived for some or all of them and compared with the test signal.
Claim 9
Dependent Claim
16 words
A system as claimed in claim 3, characterised in that a parameter examined comprises positive minimums.
Claim 10
Dependent Claim
16 words
A system as claimed in claim 3, characterised in that a parameter examined comprises negative maximums.
Claim 11
Dependent Claim
42 words
A system as claimed in claim 3, characterised in that the number of positive minimums and negative maximums are counted for each time segment, the quantised time duration of each time segment is measured and a numerical descriptor assigned in dependance thereon.
Claim 12
Dependent Claim
33 words
A system as claimed in claim 9, characterised in that the input speech signal is bandwidth limited and higher frequency signals within the band are not checked for positive minimums or negative maximums.
Claim 13
Dependent Claim
34 words
A system as claimed in claim 9, characterised in that lower frequency signals within the band are assigned the same numerical description despite differences detected in the parameter measured whereby to economise on coding.
Claim 14
Dependent Claim
30 words
A telephone set having an automatic dialling facility characterised in that it is controlled by a method as claimed in claim 1 or a system as claimed in claim 3.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.