Prosodic mimic method and apparatus

• US 20040148172A1
• Filed: 09/08/2003
• Published: 07/29/2004
• Est. Priority Date: 01/24/2003
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Voice Signal Technologies Incorporated (Microsoft Corporation)
• Inventors: Zlokarnik, Igor, Cohen, Jordan, Roth, Daniel L.
• Granted Patent: US 8,768,701 B2
• Time in Patent Office: Days
• US Class Current: 704/268
• CPC Class Codes: G10L 13/04 Details of speech synthesis systems, e.g. synthesiser structure or memory management
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A method and apparatus for synthesizing audible phrases (words) that includes capturing a spoken utterance, which may be a word, and extracting prosodic information (parameters) there from, then applying the prosodic parameters to a synthesized (nominal) word to produce a prosodic mimic word corresponding to the spoken utterance and the nominal word.

Claims

1. A method for speech synthesis, comprising:

receiving a spoken utterance;

extracting one or more prosodic parameters from the spoken utterance;

decoding the spoken utterance to provide a recognized word;

synthesizing a nominal word corresponding to the recognized word; and

generating a prosodic mimic word using the nominal word and the one or more prosodic parameters.

2. The method of claim 1, wherein the one or more prosodic parameters include pitch.

3. The method of claim 1, wherein the one or more prosodic parameters include timing.

4. The method of claim 1, wherein the one or more prosodic parameters include energy.

5. The method of claim 1, further comprising temporally aligning the spoken utterance and the nominal word.

6. The method of claim 1, further comprising temporally aligning phones of the spoken utterance and phones of the nominal word.

7. The method of claim 1, further comprising converting the prosodic mimic word into a corresponding audio signal.

8. The method of claim 1, wherein the spoken utterance is received by a telephone input device and the prosodic mimic word is provided to a telephone output device.

10. The system of claim 8, wherein the decoder comprises a speech recognition engine.

11. The system of claim 8, wherein the system is disposed on a mobile telephone device.

12. The system of claim 8, further comprising a storage device including executable instructions for speech analysis and processing.

14. The computer readable medium of claim 12, wherein the medium is disposed within a mobile telephone apparatus and operates in conjunction with a user interface.

9. A system for speech synthesis, comprising:

an audio input device that receives a spoken utterance;

a signal processor that determines one or more prosodic parameters of the spoken utterance;

a decoder that recognizes the spoken utterance and provides a corresponding recognized word;

a speech synthesizer that synthesizes a nominal word corresponding to the recognized word; and

a prosodic mimic generator that receives the nominal word and the one or more prosodic parameters and generates a prosodic mimic word.

13. A computer readable medium including stored instructions adapted for execution on a processor, including:

instructions for receiving a spoken utterance;

instructions for extracting a prosodic parameter from the spoken utterance;

instructions for decoding the spoken utterance to provide a recognized word;

instructions for synthesizing a nominal word corresponding to the recognized word; and

instructions for generating a prosodic mimic word using the nominal word and the prosodic parameter.