Word-Level Speech Recognition With a Letter to Word Encoder

Ronan Collobert, Awni Hannun, Gabriel Synnaeve,

Abstract Paper

Tue Jul 14 noon PDT [iCal] [ Join Zoom ]
Tue Jul 14 11 p.m. PDT [iCal] [ Join Zoom ]
Please do not share or post zoom links

Abstract:

We propose a direct-to-word sequence model which uses a word network to learn word embeddings from letters. The word network can be integrated seamlessly with arbitrary sequence models including Connectionist Temporal Classification and encoder-decoder models with attention. We show our direct-to-word model can achieve word error rate gains over sub-word level models for speech recognition. We also show that our direct-to-word approach retains the ability to predict words not seen at training time without any retraining. Finally, we demonstrate that a word-level model can use a larger stride than a sub-word level model while maintaining accuracy. This makes the model more efficient both for training and inference.

Chat is not available.