EP0254409A1
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Speech recognition apparatus and methods
Assignee: Smiths Group PLC
•
Filing: 1987-06-09
•
Granted: —
•
Expires: 2007-06-09
Abstract
Abstract Speech recognition apparatus has a television camera or optical array 6 that views the mouth of a speaker, and a larynogograph 20 that detects movement of the vocal folds. A microphone 5 produces an output in respect of the sound produced by the speaker. After visual processing, signals from the camera 6 are supplied to a pattern matching unit 63 together with signals from a store 64. Signals from the laryngograph are also supplied to the pattern matching unit to resolve ambiguity between speech sounds withsimilar mouth shapes. the output of the microphone is supplied to a noise adaptation unit 52 together with laryngograph output which enables external noise to be identified and rejected. After noise adaptation, the microphone output is subjected to pattern matching with a vocabulary 54 of reference templates. Signals representing the most likely fit after the two pattern matching processes are supplied to a comparator 70 which selects the most likely word spoken, or signals the speaker, via a feedback device 82, to repeat the word spoken.
Inventors
- 👤 Michael Robinson Taylor
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-08 16:33
CPC Classifications
G; G10; G10L; G10L15/00; G10L15/24; G10L15/25
Claims Analysis
Total Claims: 11
Claim 1
Independent Claim
96 words
Speech recognition apparatus, characterised in that the apparatus includes an optical device (6) mounted to view a part at least of the mouth of a speaker, the optical device providing an output that varies with movement of the speaker's mouth, voicing sensing apparatus (20) that detects movement of the speaker's vocal folds such as thereby to derive information regarding the voiced sounds of the speaker, and a processing unit (10) that derives from the output of the optical device (6) and the voicing sensing apparatus (20) information as to the speech sounds made by the speaker.
Claim 2
Dependent Claim
96 words
Speech recognition apparatus, characterised in that the apparatus includes an optical device (6) mounted to view a part at least of the mouth of a speaker, the optical device providing an output that varies with movement of the speaker's mouth, voicing sensing apparatus (20) that detects movement of the speaker's vocal folds such as thereby to derive information regarding the voiced sounds of the speaker, and a processing unit (10) that derives from the output of the optical device (6) and the voicing sensing apparatus (20) information as to the speech sounds made by the speaker.
Claim 3
Dependent Claim
32 words
Speech recognition apparatus according to Claim 1, characterised in that the voicing sensing apparatus (20) includes a laryngograph responsive to changes in impedance to electromagnetic radiation during movement of the vocal folds.
Claim 4
Dependent Claim
68 words
Speech recognition apparatus according to Claim 1 or 2, characterised in that the apparatus includes a store (64) containing information of a reference vocabulary of visual characteristics of the speaker's mouth, and a first pattern matching unit (63) that selects the closest match between the output of the optical device (6) and the vocabulary in the store (64) and provides an output representative of the selected speech sounds.
Claim 5
Dependent Claim
34 words
Speech recognition apparatus according to Claim 3, characterised in that the output from the voicing sensing apparatus (20) is supplied to the first pattern matching unit (63) to improve identification of the speech sounds.
Claim 6
Dependent Claim
64 words
Speech recognition appratus according to any one of the preceding claims, characterised in that the apparatus includes a microphone (5) that derives an output in respect of the sound produced by the speaker, and a comparator (70) that compares the output from the microphone with information derived from the optical device (6) such as to derive information concerning speech sounds made by the user.
Claim 7
Dependent Claim
39 words
Speech recognition apparatus according to Claim 5, characterised in that the output of the voicing sensing apparatus (20) and the microphone (5) are combined in order to identify sound originating from the speaker and sound originating from external sources.
Claim 8
Dependent Claim
57 words
Speech recognition apparatus according to Claim 6, characterised in that the apparatus includes a store (51, 54) containing a reference vocabulary of sound signal information, a second pattern matching unit (53) connected to the store (51, 54) and connected to receive the output of the microphone (5) after rejecting signals associated with sounds originating from external sources.
Claim 9
Dependent Claim
46 words
Speech recognition apparatus according to Claim 3 or 4 and Claim 7, characterised in that the comparator (70) receives the outputs of the first and second pattern matching units (63 and 53) and provides an output representing the most probable speech sounds made in accordance therewith.
Claim 10
Dependent Claim
30 words
Speech recognition apparatus according to any one of Claims 5 to 8, characterised in that the apparatus includes a circuit (63, 74) that modifies the output of the microphone (5).
Claim 11
Dependent Claim
56 words
Speech recognition apparatus according to Claims 7 and 9, characterised in that the output of the microphone (5) is modified by the output of the first pattern matching unit (63) and that the output of the microphone (5) is supplied to the second pattern matching unit (53) after modification by the first pattern matching unit (63).
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.