Topic tracking language model for speech recognition
| Autor: | Tomoharu Iwata, Takaaki Hori, Atsushi Sako, Shinji Watanabe, Yasuo Ariki |
|---|---|
| Rok vydání: | 2011 |
| Předmět: |
Topic model
business.industry Computer science Speech recognition Speech corpus computer.software_genre Theoretical Computer Science Human-Computer Interaction Cache language model Speaking style Tracking (education) Artificial intelligence Language model business Adaptation (computer science) computer Software Natural language processing |
| Zdroj: | Computer Speech & Language. 25:440-461 |
| ISSN: | 0885-2308 |
| DOI: | 10.1016/j.csl.2010.07.006 |
| Popis: | In a real environment, acoustic and language features often vary depending on the speakers, speaking styles and topic changes. To accommodate these changes, speech recognition approaches that include the incremental tracking of changing environments have attracted attention. This paper proposes a topic tracking language model that can adaptively track changes in topics based on current text information and previously estimated topic models in an on-line manner. The proposed model is applied to language model adaptation in speech recognition. We use the MIT OpenCourseWare corpus and Corpus of Spontaneous Japanese in speech recognition experiments, and show the effectiveness of the proposed method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect