Who Needs Words? Lexicon-Free Speech Recognition
This addresses the issue of OOV words in speech recognition for applications requiring robust vocabulary handling, though it appears incremental as it builds on existing language model approaches.
The paper tackled the problem of out-of-vocabulary words in speech recognition by showing that character-based language models perform as well as word-based models in word error rates, with lexicon-free decoding outperforming lexicon-based methods on utterances with OOV words.
Lexicon-free speech recognition naturally deals with the problem of out-of-vocabulary (OOV) words. In this paper, we show that character-based language models (LM) can perform as well as word-based LMs for speech recognition, in word error rates (WER), even without restricting the decoding to a lexicon. We study character-based LMs and show that convolutional LMs can effectively leverage large (character) contexts, which is key for good speech recognition performance downstream. We specifically show that the lexicon-free decoding performance (WER) on utterances with OOV words using character-based LMs is better than lexicon-based decoding, both with character or word-based LMs.