Language Modeling Using PLSA-Based Topic HMM
| Autor: | Tetsuya Takiguchi, Yasuo Ariki, Atsushi Sako |
|---|---|
| Rok vydání: | 2008 |
| Předmět: |
Topic model
Probabilistic latent semantic analysis business.industry Computer science Speech recognition computer.software_genre Speech processing Word accuracy ComputingMethodologies_PATTERNRECOGNITION Artificial Intelligence Hardware and Architecture Trigram Artificial intelligence Computer Vision and Pattern Recognition Language model Electrical and Electronic Engineering Transcription (software) business Hidden Markov model computer Natural language processing Software |
| Zdroj: | INTERSPEECH |
| ISSN: | 1745-1361 0916-8532 |
| DOI: | 10.1093/ietisy/e91-d.3.522 |
| Popis: | In this paper, we propose a PLSA-based language model for sports-related live speech. This model is implemented using a unigram rescaling technique that combines a topic model and an n-gram. In the conventional method, unigram rescaling is performed with a topic distribution estimated from a recognized transcription history. This method can improve the performance, but it cannot express topic transition. By incorporating the concept of topic transition, it is expected that the recognition performance will be improved. Thus, the proposed method employs a “Topic HMM” instead of a history to estimate the topic distribution. The Topic HMM is an Ergodic HMM that expresses typical topic distributions as well as topic transition probabilities. Word accuracy results from our experiments confirmed the superiority of the proposed method over a trigram and a PLSA-based conventional method that uses a recognized history. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|