English

Acoustic-to-Word Recognition with Sequence-to-Sequence Models

Audio and Speech Processing 2018-08-22 v2 Computation and Language Machine Learning Sound

Abstract

Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solution to the out-of-vocabulary problem, word models can be simpler to decode and may also be able to directly recognize semantically meaningful units. We present effective methods to train Sequence-to-Sequence models for direct word-level recognition (and character-level recognition) and show an absolute improvement of 4.4-5.0\% in Word Error Rate on the Switchboard corpus compared to prior work. In addition to these promising results, word-based models are more interpretable than character models, which have to be composed into words using a separate decoding step. We analyze the encoder hidden states and the attention behavior, and show that location-aware attention naturally represents words as a single speech-word-vector, despite spanning multiple frames in the input. We finally show that the Acoustic-to-Word model also learns to segment speech into words with a mean standard deviation of 3 frames as compared with human annotated forced-alignments for the Switchboard corpus.

Keywords

Cite

@article{arxiv.1807.09597,
  title  = {Acoustic-to-Word Recognition with Sequence-to-Sequence Models},
  author = {Shruti Palaskar and Florian Metze},
  journal= {arXiv preprint arXiv:1807.09597},
  year   = {2018}
}

Comments

9 pages, 3 figures, Under Review at SLT 2018

R2 v1 2026-06-23T03:13:56.781Z