Online LDA-Based Language Model Adaptation
| Autor: | Aleš Pražák, Jan Lehečka |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Topic model
Text corpus Perplexity Computer science business.industry 020206 networking & telecommunications 02 engineering and technology computer.software_genre Latent Dirichlet allocation Task (project management) Reduction (complexity) symbols.namesake ComputingMethodologies_PATTERNRECOGNITION 0202 electrical engineering electronic engineering information engineering symbols 020201 artificial intelligence & image processing Artificial intelligence Language model Adaptation (computer science) business computer Natural language processing |
| Zdroj: | Text, Speech, and Dialogue ISBN: 9783030007935 TSD |
| DOI: | 10.1007/978-3-030-00794-2_36 |
| Popis: | In this paper, we present our improvements in online topic-based language model adaptation. Our aim is to enhance the automatic speech recognition of a multi-topic speech which is to be recognized in the real-time (online). Latent Dirichlet Allocation (LDA) is an unsupervised topic model designed to uncover hidden semantic relationships between words and documents in a text corpus and thus reveal latent topics automatically. We use LDA to cluster the text corpus and to predict topics online from partial hypotheses during the real-time speech recognition. Based on detected topic changes in the speech, we adapt the language model on-the-fly. We are demonstrating the improvement of our system on the task of online subtitling of TV news, where we achieved \(18\%\) relative reduction of perplexity and \(3.52\%\) relative reduction of WER over non-adapted system. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|