EP0095139A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Speech synthesis from prosody data and human sound indicia data
Assignee: Texas Instruments Inc
•
Filing: 1983-05-18
•
Granted: —
•
Expires: 2003-05-18
Abstract
Abstract An electronic apparatus provides synthetic speech from a combination of prosody data and human sound indicia data. The combination of prosody data and human sound indicia data may be provided in the form of a bar code (101) read by an optical bar code reader and digitizer (102). A controller (103) receives data from the reader (102) for temporary storage in memory (104). The controller (103) utilizes the data from bar code (101) temporarily stored in the memory (104) together with an allophone library (105) to generate control signals for application to a synthesizer (106). The synthesizer (106) generates speech signals which are made audible via a speaker (107).
Inventors
- 👤 Ashok Dittakavi
- 👤 Kun-Shan Lin
- 👤 Jose Fernandez
- 👤 Bradley N. Foster
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-02 13:46
CPC Classifications
G; G10; G10L; G10L13/00; G10L13/02; G09; G09B; G09B5/00; G09B5/06; G09B5/062
Claims Analysis
Total Claims: 18
Claim 1
Independent Claim
89 words
An electronic apparatus comprising: a. pickup means for generating a sequence of input data from a printed representation, each of said input data having prosody data and a human sound indicia therein; b. control means for determining a set of synthesis parameters for each of the human sound indicia, and for combining the prosody data associated with the human sound indicia, with the corresponding set of synthesis parameters to form synthesis control data therefrom; and c. synthesis means, being responsive to said synthesis control data, for synthesizing human sounds.
Claim 2
Dependent Claim
89 words
An electronic apparatus comprising: a. pickup means for generating a sequence of input data from a printed representation, each of said input data having prosody data and a human sound indicia therein; b. control means for determining a set of synthesis parameters for each of the human sound indicia, and for combining the prosody data associated with the human sound indicia, with the corresponding set of synthesis parameters to form synthesis control data therefrom; and c. synthesis means, being responsive to said synthesis control data, for synthesizing human sounds.
Claim 3
Dependent Claim
36 words
The electronic apparatus according to claim 1 wherein said pickup means generates said input date in a sequence having a first part containing prosody data and a second part containing a sequence of human sound indicia.
Claim 4
Dependent Claim
38 words
The electronic apparatus according to claim 1 further comprised of a memory means for storing a map of the human sound indicia to the sequence of synthesis parameters and wherein said control means communicates with said memory means.
Claim 5
Dependent Claim
16 words
The electronic apparatus according to claim 3 wherein said synthesis means includes a linear predictive synthesizer.
Claim 6
Dependent Claim
36 words
The electronic apparatus according to claim 3 wherein said prosody data further includes duration and pitch data and wherein said control means includes means for combining said duration and pitch data into said synthesis control data.
Claim 7
Dependent Claim
15 words
The electronic apparatus according to claim 4 wherein said printed representation includes bar code encoding.
Claim 8
Dependent Claim
21 words
The electronic apparatus according to claim 6 wherein said prosody data defines a pitch and duration sequence for the entire phrase.
Claim 9
Dependent Claim
17 words
The electronic apparatus according to claim 1 wherein said pickup means includes a bar code reader apparatus.
Claim 10
Dependent Claim
122 words
A combination comprising: a communication medium having, a. a graphical representation, and b. machine readable synthesis data in association with said graphical representation, said synthesis data having a sequence of sets of prosody and human sound indicia; and an electronic apparatus having, a. pickup means for generating electronic input data being analaguous to said machine readable synthesis data, b. control means for determining a set of synthesis parameters for each of the human sound indicia within the sequence of electronic input data, and for combining the prosody data associated with the human sound indicia with the corresponding set of synthesis parameters to form synthesis control data therefrom, and c. synthesis means, being responsive to said synthesis control data, for synthesizing human sounds.
Claim 11
Dependent Claim
122 words
A combination comprising: a communication medium having, a. a graphical representation, and b. machine readable synthesis data in association with said graphical representation, said synthesis data having a sequence of sets of prosody and human sound indicia; and an electronic apparatus having, a. pickup means for generating electronic input data being analaguous to said machine readable synthesis data, b. control means for determining a set of synthesis parameters for each of the human sound indicia within the sequence of electronic input data, and for combining the prosody data associated with the human sound indicia with the corresponding set of synthesis parameters to form synthesis control data therefrom, and c. synthesis means, being responsive to said synthesis control data, for synthesizing human sounds.
Claim 12
Dependent Claim
45 words
The combination according to claim 9 wherein said machine readable synthesis data is disposed in said sequence of sets wherein each set comprises a sequence of data having a first part containing prosody data and a second part containing a sequence of human sound indicia.
Claim 13
Dependent Claim
15 words
The combination according to claim 9 wherein said machine readable synthesis data includes bar code.
Claim 14
Dependent Claim
16 words
The combination according to claim 11 wherein said pickup means includes a bar code reader apparatus.
Claim 15
Dependent Claim
15 words
The combination according to claim 9 wherein said synthesis means includes a linear predictive synthesizer.
Claim 16
Dependent Claim
38 words
The combination according to claim 9 wherein the sequence of sets of the machine readable synthesis data each contain duration data and wherein said control means includes means for incorporating said duration data in said synthesis control data.
Claim 17
Dependent Claim
20 words
The combination according to claim 9 wherein said prosody data defines a pitch sequence for the human readable textual phrase.
Claim 18
Dependent Claim
37 words
The combination according to claim 9 further comprised of a memory means for storing a map of the human sound indicia to the sequence of synthesis parameters and wherein said control means communicates with said memory means.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.