Large-vocabulary speech recognition method, apparatus, and medium based on multilayer central lexicons

A computer readable recording storage medium in which a program for executing a speech recognition method is recorded, the method comprising:

• layering a central lexicon in a tree structure with respect to recognition-subject vocabularies;
• detecting a speech section of a user from the speech signal whose noise is suppressed, and extracting a feature vector that will be used in recognizing a speech from the detected speech section;
• coverting sequence of the extracted feature vector into N number of candidate phoneme sequences;
• performing multi-pass symbol matching between a recognized phoneme sequence and a phonetic sequence of the central lexicon layered in the tree structure;
• and
• selecting a final speech recognition result via a Viterbi search process using a detailed acoustic model with respect to candidate vocabularies selected by the multi-pass symbol matching,
• wherein the tree structure comprises a certain node to assign to the node in the lexicon group tree and a terminal node to define lexicons which are separated from the central lexicon assigned to the node at an interval less than a predetermined standard as a neighborhood lexicons, and
• wherein the method is performed using at least one processor.

A speech recognition apparatus comprising:

• a lexicon classification unit classifying all lexicons, with respect to recognition subject vocabularies, into the tree structure;
• a feature extraction unit detecting a speech section of a user from the speech signal whose noise is suppressed, and extracting a feature vector that will be used in recognizing a speech from the detected speech section using at least one processor;
• a phoneme decoder coverting the extracted feature vector sequence into N number of candidate phoneme sequences;
• a multi-pass symbol matching unit performing multi-pass symbol matching between a recognized phoneme sequence and a phonetic sequence of a central lexicon layered in a tree structure;
• and
• a detailed matching unit performing detailed matching to select a speech recognition result using detailed acoustic model with respect to candidate vocabulary sets selected by the multi-pass symbol matching,
• wherein the tree structure comprises a certain node to assign to the node in the lexicon group tree and a terminal node to define lexicons which are separated from the central lexicon assigned to the node at an interval less than a predetermined standard as a neighborhood lexicons.

A computer-implemented speech recognition method comprising:

• detecting a speech section of a user from the speech signal whose noise is suppressed, and extracting a feature vector that will be used in recognizing a speech from the detected speech section;
• coverting sequence of the extracted feature vector into N number of candidate phoneme sequences;
• performing multi-pass symbol matching between a recognized phoneme sequence and a phonetic sequence of a central lexicon layered in a tree structure with respect to recognition-subject vocabularies;
• and
• selecting a final speech recognition result via a Viterbi search process using a detailed acoustic model with respect to candidate vocabularies selected by the multi-pass symbol matching,
• wherein the tree structure comprises a certain node to assign to the node in the lexicon group tree and a terminal node to define lexicons which are separated from the central lexicon assigned to the node at an interval less than a predetermined standard as a neighborhood lexicons, and
• wherein the method is performed using at least one processor.