Abstract | ||
---|---|---|
In this paper, we propose an end to end model for keyword spotting(KWS) with densely connected convolutional network(DenseNet) and the integration of Short Time Fourier Transform(STFT) which aims to extract utterances from raw waveform directly. Furthermore, we investigate the efficiency of adaptive and trainable window function in the task of keywords spotting. Using the recently-released Google Speech Commands Dataset as our benchmark. Our DenseNet implementation significantly outperforms previous neural networks based KWS system in terms of accuracy. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/ICDSP.2018.8631574 | DSL |
Keywords | Field | DocType |
Hidden Markov models,Computational modeling,Speech recognition,Microsoft Windows,Kernel,Training,Convolutional neural networks | Kernel (linear algebra),Pattern recognition,Computer science,Convolutional neural network,Short-time Fourier transform,Keyword spotting,Artificial intelligence,Hidden Markov model,Artificial neural network,Spotting,Window function | Conference |
ISSN | ISBN | Citations |
1546-1874 | 978-1-5386-6811-5 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xingjian Du | 1 | 1 | 3.39 |
Mengyao Zhu | 2 | 0 | 1.35 |
Mingyang Chai | 3 | 0 | 0.68 |
Xuan Shi | 4 | 29 | 6.72 |