Apparatus for electronically generating a spoken message

• US 5,727,120 A
• Filed: 10/04/1996
• Issued: 03/10/1998
• Est. Priority Date: 01/26/1995
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Lernout & Hauspie Speech Products NV (Intel Corporation)
• Inventors: Van Coile, Bert, Leys, Steven, Willems, Stefaan
• Primary Examiner(s): MacDonald, Allen R.
• Assistant Examiner(s): EDOUARD, PATRICK NESTOR
• Application Number:
  US08/725,881
• Time in Patent Office: 522 Days
• Field of Search: 395/2.15, 395/2.16, 395/2.17, 395/2.67, 395/2.69, 395/2.75, 395/2.76
• US Class Current: 704/206
• CPC Class Codes: G10L 13/02 Methods for producing synthetic speech; Speech synthesisers
• CPC Class Codes: G10L 13/04 Details of speech synthesis systems, e.g. synthesiser structure or memory management
• CPC Class Codes: G10L 13/06 Elementary speech units used in speech synthesisers; Concatenation rules
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination

Abstract

An improved apparatus for generating a spoken message is of the type formed by (i) first recording speech and (ii) then utilizing the recording so as to obtain at least one carrier, each carrier having at least one fixed part and at least one open slot, and then (iii) inserting an argument into each open slot. The improvement provides a phonetico-prosodic parameter generator for characterizing the message in terms of a sequence of phonetico-prosodic parameters for each carrier. An electronic memory stores the phonetico-prosodic parameters corresponding to each carrier and a controller constructs sequences of phonetico-prosodic parameters corresponding to the argument of each open slot. From the phonetico-prosodic parameters, a phonetics-to-speech converter generates a digital sound wave pattern which is converted, by a D/A converter, into an analog sound wave pattern. An output unit provides audible sound waves corresponding to the analog sound wave pattern. In a preferred embodiment, an input is provided for entering the arguments as orthographic or phonetic text which is converted to phonetico-prosodic parameters as well, so that the entire spoken message can be synthesized by a phonetics-to-speech system, resulting in enhanced consistency, even when the carriers are generated from the recording of different human subjects.

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.