Large vocabulary word recognition based on a graph-structured dictionary
| Autor: | K. Minamino |
|---|---|
| Rok vydání: | 2002 |
| Předmět: |
Vocabulary
Computational complexity theory business.industry Computer science Speech recognition media_common.quotation_subject Word error rate Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing) Graph theory computer.software_genre Markov model Word recognition Graph (abstract data type) Artificial intelligence business Hidden Markov model computer Computer Science::Formal Languages and Automata Theory Natural language processing media_common |
| Zdroj: | ICSLP |
| DOI: | 10.1109/icslp.1996.607222 |
| Popis: | In this paper, a structural search using a word-node graph is proposed to speed up the isolated word recognition based on hidden Markov models (HMMs). We define a distance measure for comparing pairs of words, and construct a graph containing the word distribution structure. Based on this graph, the number of words to be examined are restricted. Experiments show that the search complexity is considerably reduced with little degradation of the recognition accuracy. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|