Dynamic adjustment of language models for automatic speech recognition using word similarity
Authors:
- 9 February 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 426-432
Abstract
Out-of-vocabulary (OOV) words can pose a particular problem for automatic speech recognition (ASR) of broadcast news. The language models (LMs) of ASR systems are typically trained on static corpora, whereas new words (particularly new proper nouns) are continually introduced in the media. Additionally, such OOVs are often content-rich proper nouns that are vital to understanding the topic. In this work, we explore methods for dynamically adding OOVs to language models by adapting the n-gram language model used in our ASR system. We propose two strategies: the first relies on finding in-vocabulary (IV) words similar to the OOVs, where word embeddings are used to define similarity. Our second strategy leverages a small contemporary corpus to estimate OOV probabilities. The models we propose yield improvements in perplexity over the baseline; in addition, the corpus-based approach leads to a significant decrease in proper noun error rate over the baseline in recognition experiments.Keywords
This publication has 6 references indexed in Scilit:
- Document level semantic context for retrieving OOV proper names2016
- OOV Proper Name retrieval using topic and lexical context models2015
- Class-Based N-Gram Language Model for New Words Using Out-of-Vocabulary to In-Vocabulary SimilarityIEICE Transactions on Information and Systems, 2012
- Automatically finding semantically consistent n-grams to add new words in LVCSR systems2011
- Open Vocabulary ASR for Audiovisual Document Indexation2006
- Some statistical issues in the comparison of speech recognition algorithms2003