TTS-generated numeric training data plus a compact neural denormalizer improve E2E ASR word error rates on numeric sequences by up to a factor of 8 for the longest cases.
tagger” RNN to run on the input sequence before the sequence-to-sequence model. The tagger tags each word in the input sequence as either “trivial
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Improving Performance of End-to-End ASR on Numeric Sequences
TTS-generated numeric training data plus a compact neural denormalizer improve E2E ASR word error rates on numeric sequences by up to a factor of 8 for the longest cases.