Whole-Word Segmental Speech Recognition with Acoustic Word Embeddings
This work addresses the problem of efficient whole-word speech recognition for applications requiring direct acoustic-to-word mapping, though it is incremental as it builds on prior A2W models.
The paper tackles the computational challenge of whole-word segmental speech recognition by proposing an efficient GPU-based approach with a simple segment scoring function, achieving a large reduction in word error rate through pre-training with acoustic word embeddings and acoustically grounded word embeddings.
Segmental models are sequence prediction models in which scores of hypotheses are based on entire variable-length segments of frames. We consider segmental models for whole-word ("acoustic-to-word") speech recognition, with the feature vectors defined using vector embeddings of segments. Such models are computationally challenging as the number of paths is proportional to the vocabulary size, which can be orders of magnitude larger than when using subword units like phones. We describe an efficient approach for end-to-end whole-word segmental models, with forward-backward and Viterbi decoding performed on a GPU and a simple segment scoring function that reduces space complexity. In addition, we investigate the use of pre-training via jointly trained acoustic word embeddings (AWEs) and acoustically grounded word embeddings (AGWEs) of written word labels. We find that word error rate can be reduced by a large margin by pre-training the acoustic segment representation with AWEs, and additional (smaller) gains can be obtained by pre-training the word prediction layer with AGWEs. Our final models improve over prior A2W models.