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.
A neural attention model for speech command recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper introduces a convolutional recurrent network with attention for speech command recognition. Attention models are powerful tools to improve performance on natural language, image captioning and speech tasks. The proposed model establishes a new state-of-the-art accuracy of 94.1% on Google Speech Commands dataset V1 and 94.5% on V2 (for the 20-commands recognition task), while still keeping a small footprint of only 202K trainable parameters. Results are compared with previous convolutional implementations on 5 different tasks (20 commands recognition (V1 and V2), 12 commands recognition (V1), 35 word recognition (V1) and left-right (V1)). We show detailed performance results and demonstrate that the proposed attention mechanism not only improves performance but also allows inspecting what regions of the audio were taken into consideration by the network when outputting a given category.
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.