Dynamic adjustment of language models for automatic speech recognition using word similarity

Anna Currey (1) , Irina Illina (1) , Dominique Fohr (1)

1 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication

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.

Mots clés: ASR; language modeling; OOV; word embeddings; lexicon extension

Domaines: Interface homme-machine [cs.HC]; Informatique et langage [cs.CL]

Anna Currey, Irina Illina, Dominique Fohr. Dynamic adjustment of language models for automatic speech recognition using word similarity . IEEE Workshop on Spoken Language Technology (SLT 2016), Dec 2016, San Diego, CA, United States. ⟨hal-01384365⟩