Continuous speech recognizing apparatus and a recording medium thereof

• US 6,393,398 B1
• Filed: 11/22/1999
• Issued: 05/21/2002
• Est. Priority Date: 09/22/1999
• Status: Active Grant

• Current Assignee: Nippon Hoso Kyokai
• Original Assignee: Nippon Hoso Kyokai
• Inventors: Ando, Akio, Imai, Toru
• Primary Examiner(s): Korzuch, William
• Assistant Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US09/447,391
• Time in Patent Office: 911 Days
• Field of Search: 704/251, 704/252, 704/254, 704/255, 704/256
• US Class Current: 704/254
• CPC Class Codes: G10L 15/08 Speech classification or search

Abstract

A second pass processor detects a stable portion in a 1-best word string obtained by a second pass processing, and determines the word string in the detected stable portion as a speech recognition result.

Claims

1. A continuous speech recognizing apparatus that obtains from input continuous speech a plurality of speech recognition candidates of a word string using a simple probabilistic language model in a first pass processor, and that determines a speech recognition result of the plurality of speech recognition candidates using a complex probabilistic language model in a second pass processor, wherein

said first pass processor obtains word strings of the plurality of speech recognition candidates of the continuous speech at fixed time intervals from an input start time, and

said second pass processor comprises:

word string selecting means for selecting, using the complex probabilistic language model, a maximum likelihood word string from among the word strings of the plurality of speech recognition candidates obtained at the fixed time intervals, and

speech recognition result determining means for detecting a stable portion in word strings detected at every fixed intervals, and for successively determining a word string of the stable portion as the speech recognition result.

2. The continuous speech recognizing apparatus as claimed in claim 1, wherein said speech recognition result determining means comprises:

a comparator for comparing a first word string with a second word string, the first word string consisting of a word string currently detected by said word string selecting means with the exception of a final portion of the word string, and the second word string consisting of a speech recognition candidates previously obtained by said word string selecting means; and

a determining section for determining, when said comparator makes a decision that a same word string as the second word string is contained in the first word string, the second word string as the speech recognition result.

3. The continuous speech recognizing apparatus as claimed in claim 1, wherein said first pass processor obtains the plurality of speech recognition candidates by tracing back a word lattice beginning from a phoneme with a maximum score as of now when a plurality of speech recognition candidates of a word string are obtained by using the simple probabilistic language model.

4. The continuous speech recognizing apparatus as claimed in claim 3, wherein trace back timing of the word lattice is made variable.

5. The continuous speech recognizing apparatus as claimed in claim 3, wherein said first pass processor traces back the word lattice beginning from a plurality of currently active phonemes.

6. A recording medium having a computer executable program code means for obtaining from input continuous speech a plurality of speech recognition candidates of a word string using a simple probabilistic language model in a first pass, and for determining a speech recognition result of the plurality of speech recognition candidates using a complex probabilistic language model in a second pass, wherein

said first pass comprises a step of obtaining, beginning from an input start time, word strings of the plurality of speech recognition candidates of the continuous speech at fixed time intervals, and

said second pass comprises:

a word string selecting step of selecting, using the complex probabilistic language model, a maximum likelihood word string from among the word strings of the plurality of speech recognition candidates obtained at the fixed time intervals, and

speech recognition result determining step of detecting a stable portion in word strings detected at every fixed intervals, and of successively determining a word string of the stable portion as the speech recognition result.

7. The recording medium as claimed in claim 6, wherein said speech recognition result determining step comprises:

a comparing step of comparing a first word string with a second word string, the first word string consisting of a word string currently detected in said word string selecting step with the exception of a final portion of the word string, and the second word string consisting of speech recognition candidates previously obtained in said word string selecting step; and

a determining step of determining, when said comparing step makes a decision that a same word string as the second word string is contained in the first word string, the second word string as the speech recognition result.

8. The recording medium as claimed in claim 6, wherein said first pass obtains the plurality of speech recognition candidates by tracing back a word lattice beginning from a phoneme with a maximum score as of now when a plurality of speech recognition candidates of a word string are obtained by using the simple probabilistic language model.

9. The recording medium as claimed in claim 8, wherein trace back timing of the word lattice is made variable.

10. The recording medium as claimed in claim 8, wherein said first pass traces back the word lattice beginning from a plurality of currently active phonemes.