Speech information processing method and apparatus and storage medium using a segment pitch pattern model

• US 7,155,390 B2
• Filed: 10/18/2004
• Issued: 12/26/2006
• Est. Priority Date: 03/31/2000
• Status: Expired due to Fees

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Fukada, Toshiaki
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US10/965,854
• Publication Number:
  US 20050055207A1
• Time in Patent Office: 799 Days
• Field of Search: None
• US Class Current: 704/254
• CPC Class Codes: G10L 13/10 Prosody rules derived from text; Stress or intonation
• CPC Class Codes: G10L 15/1807 using prosody or stress

Abstract

A speech information processing apparatus and method performs speech recognition. Speech is input, and feature parameters of the input speech are extracted. The feature parameters are recognized based on a segment pitch pattern model. The segment pitch pattern model may be obtained by modeling time change in a fundamental frequency of a phoneme belonging to a predetermined phonemic environment with a polynomial segment model. The segment pitch pattern model may also be obtained by modeling with at least one of a single mixed distribution and a multiple mixed distribution.

Claims

1. A speech information processing method comprising:

an input step of inputting speech;

an extraction step of extracting a feature parameter of the speech; and

a speech recognition step of recognizing the feature parameter based on a segment pitch pattern model,

wherein the segment pitch pattern model is obtained by modeling time change in a fundamental frequency of a phoneme belonging to a predetermined phonemic environment with a polynomial segment model.

3. A computer-readable storage medium holding a program for executing the speech information processing method claimed in claim 1.

2. A speech information processing method comprising:

an input step of inputting speech;

an extraction step of extracting a feature parameter of the speech; and

a speech recognition step of recognizing the feature parameter based on a segment pitch pattern model,

wherein the segment pitch pattern model is obtained by modeling with at least one of a single mixed distribution and a multiple mixed distribution.

6. A computer-readable storage medium holding a program for executing the speech information processing method claimed in claim 2.

4. A speech information processing apparatus comprising:

input means for inputting speech;

extraction means for extracting a feature parameter of the speech; and

speech recognition means for recognizing the feature parameter based on a segment pitch pattern model,

wherein the segment pitch pattern model is obtained by modeling time change in a fundamental frequency of a phoneme belonging to a predetermined phonemic environment with a polynomial segment model.

5. A speech information processing apparatus comprising:

input means for inputting speech;

extraction means for extracting a feature parameter of the speech; and

speech recognition means for recognizing the feature parameter based on a segment pitch pattern model,

wherein the segment pitch pattern model is obtained by modeling with at least one of a single mixed distribution and a multiple mixed distribution.