JPS6310439B2 - - Google Patents

Description

[Detailed description of the invention]

The present invention relates to a word speech recognition method that first performs phoneme recognition on input speech and then recognizes words by comparing this recognized phoneme sequence with a word dictionary in which phonemes are expressed. The present invention provides a voice recognition method. A conventional word recognition method will be explained with reference to FIG. As shown in FIG. 1, input speech is first analyzed, features of the input word speech are extracted, and phonemes making up the input word speech are recognized. This recognized phoneme sequence is compared with the dictionary phoneme sequence of each dictionary entry in the word dictionary, and the likelihood between the two phoneme sequences is calculated using a Confusion Matrix (hereinafter abbreviated as CM) between the phonemes. The recognition probability is calculated for each phoneme using the above method, and the dictionary entry with the maximum likelihood between phoneme sequences is determined as a recognized word. Table 1 shows an example of a word dictionary used in the word speech recognition method, and each word is written according to the phoneme notation shown in Table 2. FIG. 2 shows a part of the CM. In FIG. 2, the vertical lines indicate phonemes in the word dictionary, and the horizontal lines indicate recognized phonemes. Further, the numbers in FIG. 2 indicate the probability of what kind of phoneme each phoneme in the word dictionary is recognized as, expressed in percentage. For example, in Figure 2, the probability that the phoneme I in the word dictionary will be recognized as I is 75%, the probability that it will be recognized as U is 5%, and the probability that it will be recognized as A is 0.
%, the probability of dropping out is 8%, etc.

【table】

Claims (1)

[Claims] 1 Perform phoneme recognition on the input speech to obtain a recognized phoneme sequence, and recognize words by calculating the likelihood between this recognized phoneme sequence and the dictionary phoneme sequence of each dictionary item in the word dictionary with phoneme notation. In this case, a likelihood weight value is determined in advance for each dictionary item, and a weighted likelihood value is calculated by adding or multiplying this likelihood weight value to the likelihood between the phoneme sequences. A word speech recognition method characterized in that a dictionary item with a maximum degree value is recognized as a word.