Word-Level Speech Recognition With a Letter to Word Encoder

By Ronan Collobert, Awni Y. Hannun, Gabriel Synnaeve. 2019

12 citations recorded by the source corpus.

Subfields: Speech & Audio

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Speech & Audio

1. Jinyu Li

Citations in the corpus

• Recent Advances in End-to-End Automatic Speech Recognition (2021, background): “Although there are few works that allow injecting any out-ofvocabulary word into the vocabulary of acoustic-to-word E2E models during inference via subword-to-word embedding [45, 247], this problem is far from being solved.”
• slimIPL: Language-Model-Free Iterative Pseudo-Labeling (2020, unknown): “Stride Tokens Criterion LM Dev WER Test WER clean other clean other RWTH [76] - - hybrid word 4-gram 5.0 19.5 5.8 18.6 S2S - 14.7 38.5 14.7 40.8 DeCoAR [47] - phonemes CTC - - - 6.10 17.43 Word-level [77] 80ms 5k wp CTC - 12.4 27.7 12.8 28.7 wp 6-gram 9.7 22.9 10.3 24.0 S2S - 9.0 22.8 9.5 23.3 wp 6-”