Word-Level Speech Recognition With a Letter to Word Encoder
ICML, pp. 2100-2110, 2020.
We have demonstrated that a direct-to-word approach for speech recognition is possible but promising
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 gai...More
PPT (Upload PPT)