EP0239394A1
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Speech synthesis system
Assignee: International Business Machines Corp
•
Filing: 1987-03-25
•
Granted: —
•
Expires: 2007-03-25
Abstract
Abstract The present invention relates to a speech synthesis system of the type which comprises synthesis parameter generating means (5, 6, 7, 8, 10, 11) for generating reference synthesis parameters (p, q) representing items of speech, and storage means (4) for storing the reference synthesis parameters. The system also comprises input means (1) for receiving an item of text to be synthesised, analysis means (15) for analysing the item of text, calculating means (13, 16) utilising the stored reference synthesis parameters and the results of the analysis of the item of text to create a set of operational synthesis parameters representing the item of text, and synthetic speech generating means (6, 7, 9, 17) utilising the created set of operational synthesis parameters to generate synthesised speech representing the item of text. According to the invention the system is characterised in that the synthesis parameter generating means comprises means for generating a first set of reference synthesis parameters in response to the receipt of a first item of natural speech, and means for generating a second set of reference synthesis parameters in response to the receipt of a second item of natural speech. The calculating means utilises the first and second set of reference synthesis parameters in order to create the set of operational synthesis parameters representing the item of text.
Inventors
- 👤 Hiroshi Kaneko
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-10-27 10:15
CPC Classifications
G; G10; G10L; G10L13/00; G10L13/08
Claims Analysis
Total Claims: 11
Claim 1
Independent Claim
199 words
A speech synthesis system comprising synthesis parameter generating means (5, 6, 7, 8, 10, 11) for generating reference synthesis parameters (p, q) representing items of speech, storage means (4) for storing said reference synthesis parameters, input means (1) for receiving an item of text to be synthesised, analysis means (15) for analysing said item of text, calculating means (13, 16) utilising said stored reference synthesis parameters and the results of the analysis of said item of text to create a set of operational synthesis parameters representing said item of text, and synthetic speech generating means (6, 7, 9, 17) utilising said created set of operational synthesis parameters to generate synthesised speech representing said item of text, characterised in that said synthesis parameter generating means comprises, means for generating a first set of reference synthesis parameters in response to the receipt of a first item of natural speech, and means for generating a second set of reference synthesis parameters in response to the receipt of a second item of natural speech, and said calculating means utilises said first and second set of reference synthesis parameters in order to create said set of operational synthesis parameters representing said item of text.
Claim 2
Dependent Claim
199 words
A speech synthesis system comprising synthesis parameter generating means (5, 6, 7, 8, 10, 11) for generating reference synthesis parameters (p, q) representing items of speech, storage means (4) for storing said reference synthesis parameters, input means (1) for receiving an item of text to be synthesised, analysis means (15) for analysing said item of text, calculating means (13, 16) utilising said stored reference synthesis parameters and the results of the analysis of said item of text to create a set of operational synthesis parameters representing said item of text, and synthetic speech generating means (6, 7, 9, 17) utilising said created set of operational synthesis parameters to generate synthesised speech representing said item of text, characterised in that said synthesis parameter generating means comprises, means for generating a first set of reference synthesis parameters in response to the receipt of a first item of natural speech, and means for generating a second set of reference synthesis parameters in response to the receipt of a second item of natural speech, and said calculating means utilises said first and second set of reference synthesis parameters in order to create said set of operational synthesis parameters representing said item of text.
Claim 3
Dependent Claim
89 words
A speech synthesis system as claimed in claim 1 characterised in that said first item of natural speech is spoken at a relatively high speed, said second item of natural speech is spoken at a relatively low speed, said calculating means interpolates between said first and second set of reference synthesis parameters in order to create said set of operational synthesis parameters representing said item of text, and said synthetic speech generating means generates synthesised speech at a speed between said relatively high speed and said relatively low speed.
Claim 4
Dependent Claim
70 words
A speech synthesis system as claimed in claim 2 characterised in that said calculating means comprises means for calculating an interpolation variable based on the required duration of said synthesised speech, and means for utilising said interpolation variable to control the creation of said set of operational synthesis parameters so that said synthesised speech is generated at the required speed between said relatively high speed and said relatively low speed.
Claim 5
Dependent Claim
77 words
A speech synthesis system as claimed in any one of the preceding claims characterised in that said synthesis parameter generating means comprises means for generating a third set of reference synthesis parameters in response to the receipt of a third item of natural speech, and said calculating means utilises any two of said first, second and third sets of reference synthesis parameters in order to create said set of operational synthesis parameters representing said item of text.
Claim 6
Dependent Claim
49 words
A speech synthesis system as claimed in any one of the preceding claims characterised in that said synthesis parameter generating means comprises means for subdividing each item of natural speech into a set of time periods, and means for generating reference synthesis parameters for each of said time periods.
Claim 7
Dependent Claim
62 words
A speech synthesis system as claimed in any one of the preceding claims characterised in that said synthesis parameter generating means comprises means for comparing said sets of reference synthesis parameters with each other in order to obtain a parameter variation factor, and said calculating means utilises said parameter variation factor to control the creation of said set of operational synthesis parameters.
Claim 8
Dependent Claim
46 words
A speech synthesis system as claimed in any one of the preceding claims characterised in that said synthesis parameter generating means comprises means for training said sets of reference synthesis parameters in order to avoid errors in the creation of said set of operational synthesis parameters.
Claim 9
Independent Claim
163 words
A method of generating synthesised speech comprising generating reference synthesis parameters (p, q) representing items of speech, storing said reference synthesis parameters, receiving an item of text to be synthesised, analysing said item of text, utilising said stored reference synthesis parameters and the results of the analysis of said item of text to create a set of operational synthesis parameters representing said item of text, and utilising said created set of operational synthesis parameters to generate synthesised speech representing said item of text, characterised in that said reference synthesis parameters are generated by generating a first set of reference synthesis parameters in response to the receipt of a first item of natural speech, and generating a second set of reference synthesis parameters in response to the receipt of a second item of natural speech, and in that said first and second set of reference synthesis parameters are used in order to create said set of operational synthesis parameters representing said item of text.
Claim 10
Independent Claim
163 words
A method of generating synthesised speech comprising generating reference synthesis parameters (p, q) representing items of speech, storing said reference synthesis parameters, receiving an item of text to be synthesised, analysing said item of text, utilising said stored reference synthesis parameters and the results of the analysis of said item of text to create a set of operational synthesis parameters representing said item of text, and utilising said created set of operational synthesis parameters to generate synthesised speech representing said item of text, characterised in that said reference synthesis parameters are generated by generating a first set of reference synthesis parameters in response to the receipt of a first item of natural speech, and generating a second set of reference synthesis parameters in response to the receipt of a second item of natural speech, and in that said first and second set of reference synthesis parameters are used in order to create said set of operational synthesis parameters representing said item of text.
Claim 11
Dependent Claim
84 words
A method of generating synthesised speech as claimed in claim 8 characterised in that said first item of natural speech is spoken at a relatively high speed, and said second item of natural speech is spoken at a relatively low speed, and in that said set of operational synthesis parameters are created by interpolating between said first and second set of reference synthesis parameters so that said synthesised speech is generated at a speed between said relatively high speed and said relatively low speed.
References Cited (Backward Citations)
WO1983003483A1
Cited
EP0140777A1
Cited
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.