Speech recognition apparatus, speech recognition method, and recording medium

• US 20040167779A1
• Filed: 02/24/2004
• Published: 08/26/2004
• Est. Priority Date: 03/14/2000
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Minamino, Katsuki, Lucke, Helmut, Asano, Yasuharu, Ogawa, Hiroaki
• Granted Patent: US 7,249,017 B2
• Time in Patent Office: Days
• US Class Current: 704/240
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units

Abstract

In order to prevent degradation of speech recognition accuracy due to an unknown word, a dictionary database has stored therein a word dictionary in which are stored, in addition to words for the objects of speech recognition, suffixes, which are sound elements and a sound element sequence, which form the unknown word, for classifying the unknown word by the part of speech thereof. Based on such a word dictionary, a matching section connects the acoustic models of an sound model database, and calculates the score using the series of features output by a feature extraction section on the basis of the connected acoustic model. Then, the matching section selects a series of the words, which represents the speech recognition result, on the basis of the score.

Claims

1. A speech recognition apparatus for calculating a score indicating the likelihood of a speech recognition result of input speech and for performing continuous speech recognition on said speech based on the score, said speech recognition apparatus comprising:

extraction means for extracting features of said speech from said speech;

calculation means for calculating said score using said features on the basis of a dictionary in which unknown-word-forming elements, which are elements forming an unknown word, for classifying an unknown word by an attribute thereof and words for the object of speech recognition are entered; and

selection means for selecting a series of said words, which represents a speech recognition result, on the basis of said score.

2. A speech recognition apparatus according to claim 1, wherein in said dictionary, the unknown-word-forming elements for classifying an unknown word by a part of speech thereof are entered.

3. A speech recognition apparatus according to claim 2, wherein in said dictionary, suffixes are entered as said unknown-word-forming elements.

4. A speech recognition apparatus according to claim 3, wherein in said dictionary, phonemes which form an unknown word are entered together with said suffixes.

5. A speech recognition apparatus according to claim 1, wherein in said dictionary, unknown-word-forming elements for classifying an unknown word by a language thereof are entered.

6. A speech recognition apparatus according to claim 1, further comprising said dictionary.

7. A speech recognition method for calculating a score indicating the likelihood of a speech recognition result of input speech and for performing continuous speech recognition on said speech based on the score, said speech recognition method comprising the steps of:

extracting features of said speech from said speech;

calculating said score using said features on the basis of a dictionary in which unknown-word-forming elements, which are elements forming an unknown word, for classifying an unknown word by an attribute thereof and words for the object of speech recognition are entered; and

selecting a series of said words, which represents a speech recognition result, on the basis of said score.

8. A recording medium having a program recorded therein, said program comprising the steps of:

extracting features of said speech from said speech;

calculating said score using said features on the basis of a dictionary in which unknown-word-forming elements, which are elements forming an unknown word, for classifying an unknown word by an attribute thereof and words for the object of speech recognition are entered; and

selecting a series of said words, which represents a speech recognition result, on the basis of said score.