Speech-based pronunciation symbol searching device, method and program using correction distance
First Claim
1. A searching device, comprising:
- circuitry configured to;
subject input speech to speech recognition;
match a pronunciation symbol string for search results and a recognition result pronunciation symbol string based on calculation of a correction distance, for each of a plurality of word strings for search results, wherein said plurality of word strings for search results are to be search results for word strings that correspond to said input speech,wherein said pronunciation symbol string for search results is an array of pronunciation symbols that express pronunciation of each of said plurality of word strings for search results, and each of said pronunciation symbols is a symbol that expresses pronunciation of a syllable or a phoneme,wherein said recognition result pronunciation symbol string is an array of pronunciation symbols that express pronunciation of speech recognition results of said input speech, andwherein said circuitry is configured to calculate said correction distance based on a relationship between a vector for search results which is a vector that expresses said pronunciation symbol string for search results, a recognition result vector which is a vector that expresses said recognition result pronunciation symbol string, and a square root of a value obtained by multiplication of a size of said vector for search results and a size of said recognition result vector; and
output a search result word string which is a result of search for said word strings that correspond to said input speech from said plurality of word strings for search results, based on matching results of said pronunciation symbol string for search results and said recognition result pronunciation symbol string for each of said plurality of word strings for search results.
1 Assignment
0 Petitions
Accused Products
Abstract
The present invention relates to a searching device, searching method, and program whereby searching for a word string corresponding to input voice can be performed in a robust manner.
A voice recognition unit 11 subjects an input voice to voice recognition. A matching unit 16 performs matching, for each of multiple word strings for search results which are word strings that are to be search results for word strings corresponding to the input voice, of a pronunciation symbol string for search results, which is an array of pronunciation symbols expressing pronunciation of the word string search result, and a recognition result pronunciation symbol string which is an array of pronunciation symbols expressing pronunciation of the voice recognition results of the input voice. An output unit 17 outputs a search result word string which is the result of searching the word strings corresponding to the input voice from the multiple word strings for search results, based on the matching results of the pronunciation symbol string for search results and the recognition result pronunciation symbol string. The present invention can be applied in the case of performing voice searching, for example.
-
Citations
11 Claims
-
1. A searching device, comprising:
circuitry configured to; subject input speech to speech recognition; match a pronunciation symbol string for search results and a recognition result pronunciation symbol string based on calculation of a correction distance, for each of a plurality of word strings for search results, wherein said plurality of word strings for search results are to be search results for word strings that correspond to said input speech, wherein said pronunciation symbol string for search results is an array of pronunciation symbols that express pronunciation of each of said plurality of word strings for search results, and each of said pronunciation symbols is a symbol that expresses pronunciation of a syllable or a phoneme, wherein said recognition result pronunciation symbol string is an array of pronunciation symbols that express pronunciation of speech recognition results of said input speech, and wherein said circuitry is configured to calculate said correction distance based on a relationship between a vector for search results which is a vector that expresses said pronunciation symbol string for search results, a recognition result vector which is a vector that expresses said recognition result pronunciation symbol string, and a square root of a value obtained by multiplication of a size of said vector for search results and a size of said recognition result vector; and output a search result word string which is a result of search for said word strings that correspond to said input speech from said plurality of word strings for search results, based on matching results of said pronunciation symbol string for search results and said recognition result pronunciation symbol string for each of said plurality of word strings for search results. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
10. A searching method to search for a word string corresponding to input speech, said searching method comprising:
-
subjecting said input speech to speech recognition; matching, using circuitry, a pronunciation symbol string for search results and a recognition result pronunciation symbol string based on calculation of a correction distance, regarding each of a plurality of word strings for search results, wherein said plurality of word strings for search results are to be search results for word strings corresponding to said input speech, said pronunciation symbol string for search results being an array of pronunciation symbols expressing pronunciation of each of said plurality of word strings for search results, and each of said pronunciation symbols being a symbol expressing pronunciation of a syllable or a phoneme, said recognition result pronunciation symbol string being an array of pronunciation symbols expressing pronunciation of speech recognition results of said input speech, wherein said correction distance is calculated based on a relationship between a vector for search results which is a vector that expresses said pronunciation symbol string for search results, a recognition result vector which is a vector that expresses said recognition result pronunciation symbol string, and a square root of a value obtained by multiplication of a size of said vector for search results and a size of said recognition result vector; and outputting a search result word string, which is a result of searching said word strings corresponding to said input speech from said plurality of word strings for search results, based on matching results of said pronunciation symbol string for search results and said recognition result pronunciation symbol string regarding each of said plurality of word strings for search results.
-
-
11. A non-transitory computer-readable storage medium including computer-executable instructions, which when executed by a computer cause said computer to execute operations, comprising:
-
subjecting input speech to speech recognition; matching a pronunciation symbol string for search results and a recognition result pronunciation symbol string by calculating a correction distance, regarding each of a plurality of word strings for search results, wherein said plurality of word strings for search results are to be search results for word strings corresponding to said input speech, said pronunciation symbol string for search results being an array of pronunciation symbols expressing pronunciation of each of said plurality of word strings for search results, and each of said pronunciation symbols being a symbol expressing pronunciation of a syllable or a phoneme, said recognition result pronunciation symbol string being an array of pronunciation symbols expressing pronunciation of speech recognition results of said input speech, wherein said correction distance is calculated based on a relationship between a vector for search results which is a vector that expresses said pronunciation symbol string for search results, a recognition result vector which is a vector that expresses said recognition result pronunciation symbol string, and a square root of a value obtained by multiplication of a size of said vector for search results and a size of said recognition result vector; and outputting a search result word string which is a result of searching said word strings corresponding to said input speech from said plurality of word strings for search results, based on matching results of said pronunciation symbol string for search results and said recognition result pronunciation symbol string regarding each of said plurality of word strings for search results.
-
Specification