Method and system for recognizing a boundary between contiguous sounds for use with a speech recognition system

• US 5,812,973 A
• Filed: 08/09/1996
• Issued: 09/22/1998
• Est. Priority Date: 09/30/1994
• Status: Expired due to Term

• Current Assignee: Google Technology Holdings LLC (Alphabet Inc.)
• Original Assignee: Motorola, Inc. (Motorola Solutions, Inc.)
• Inventors: Wang, Shay-Ping Thomas
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US08/700,662
• Time in Patent Office: 774 Days
• Field of Search: 395/2.6, 395/2.62, 395/2.63, 395/2.64, 395/2.65, 395/2.66, 395/2.49, 395/2.5, 395/2.4, 395/2.41
• US Class Current: 704/253
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/04 Segmentation; Word boundary detection
• CPC Class Codes: G10L 15/05 Word boundary detection
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• CPC Class Codes: G10L 25/18 the extracted parameters being spectral information of each sub-band
• CPC Class Codes: G10L 25/24 the extracted parameters being the cepstrum
• CPC Class Codes: G10L 25/30 using neural networks

Abstract

Boundaries of spoken sounds in continuous speech are identified by classifying delimitative sounds to provide improved performance in a speech-recognition system. Delimitative sounds, those portions of continuous speech that occur between two spoken sounds, are recognized by the same method used to recognize spoken sounds. Recognition of delimitative sounds is accomplished by training a learning machine to act as a classifier which implements a discriminant function based on a polynomial expansion.

Claims

1. In a speech recognition system, a method for recognizing a boundary between two contiguous spoken sounds, the method comprising the steps of:

defining a delimitative spoken sound which represents the boundary;

receiving continuously spoken speech that includes the delimitative spoken sound;

extracting at least one feature from the continuously spoken speech corresponding to the delimitative spoken sound; and

recognizing the boundary by classifying the at least one feature according to a polynomial discriminant function.

2. The method of claim 1, wherein the step of recognizing includes the following sub-step:

classifying the at least one feature according to a polynomial discriminant function having a form ##EQU3## wherein y represents a classifier output, w_i-1 represents a coefficient of an ith term in the polynomial function, x_l, x₂, . . . , x_n represent a plurality of features including the at least one feature, g_1i, . . . , g_ni represent exponents for the ith term in the polynomial function, and i, m, and n are integers.

3. The method of claim 1, wherein the at least one feature corresponds to the continuously spoken speech during an interval of time having a duration.

4. The method of claim 3, wherein the duration of the interval of time is 10 milliseconds.

5. The method of claim 1, wherein the at least one feature is selected from the group consisting of cepstral coefficients, predictive coefficients, and Fourier coefficients.