Claims
- 1. An improved apparatus for generating a spoken message of the type employing a recording of the message spoken by a human voice, the recording being parsed into at least one carrier, each carrier having at least one fixed part and at east one open slot, an argument being inserted into each open slot, wherein the improvement comprises:
- a. a phonetico-prosodic parameter generator operating on the recording with prosody transplantation techniques for characterizing the message in terms of phonetico-prosodic parameters;
- b. an electronic memory for storing phonetico-prosodic parameters corresponding to each carrier;
- c. a controller for constructing sequences of phonetico-prosodic parameters corresponding to the argument of each open slot;
- d. a phonetics-to-speech converter for generating a digital sound wave pattern from the sequences of phonetico-prosodic parameters;
- e. a D/A converter for generating an analog sound wave pattern from the digital sound wave pattern; and
- f. an output unit for providing audible sound waves corresponding to the analog sound wave pattern.
- 2. An apparatus according to claim 1, further comprising an input device for reading an argument in orthographic or phonetic text format.
- 3. An apparatus for electronically generating a spoken message from phonetico-prosodic parameters, the spoken message having at least one carrier, each carrier having at least one fixed part and at least one open slot, an argument being inserted into each open slot, the apparatus comprising:
- a. a first controller for selecting at least one carrier to form the spoken message;
- b. an electronic memory for storing phonetico-prosodic parameters derived from a recording using prosody transplantation techniques, said parameters corresponding to each carrier;
- c. a second controller for constructing sequences of phonetico-prosodic parameters corresponding to the argument of each open slot;
- d. a phonetics-to-speech converter for generating a digital sound wave pattern from the sequences of phonetico-prosodic parameters and each selected carrier;
- e. a D/A converter for generating an analog sound wave pattern from the digital sound wave pattern; and
- f. an output unit for providing audible sound waves corresponding to the analog sound wave pattern.
Parent Case Info
This application is a divisional application of Ser. No. 08/379,330, filed Jan. 26, 1995, incorporated herein by reference now U.S. Pat. No. 5,592,585.
US Referenced Citations (5)
Non-Patent Literature Citations (1)
Entry |
E. Moulins et al., "New Approaches For Improving The Quality text-to-speech". Proceedings of Verba 90, International Conference of Speech Technologies, Roma, 22-24, Jan., 19909, pp. 310-319. |
Divisions (1)
|
Number |
Date |
Country |
Parent |
379330 |
Jan 1995 |
|