Introduces multi-layer attention for keyword spotting that incorporates pre-extraction layer information to reduce bias in LSTM attention weights, reporting favorable results versus CNN and bi-LSTM baselines on Google Speech Commands V2.
Fast and Accurate Recurrent Neural Network Acoustic Models for Speech Recognition[C] INTERSPEECH 2015 proceedings
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multi-layer Attention Mechanism for Speech Keyword Recognition
Introduces multi-layer attention for keyword spotting that incorporates pre-extraction layer information to reduce bias in LSTM attention weights, reporting favorable results versus CNN and bi-LSTM baselines on Google Speech Commands V2.