Title | ||
---|---|---|
End-to-end acoustic modeling using convolutional neural networks for HMM-based automatic speech recognition. |
Abstract | ||
---|---|---|
•Novel CNN-based end-to-end acoustic modeling approach is proposed.•Relevant features are automatically learned from the signal by discriminating phones.•Learned features are more discriminative than cepstral-based features.•Learned features are somewhat invariant to languages and domains.•Proposed approach leads to better ASR systems. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1016/j.specom.2019.01.004 | Speech Communication |
Keywords | Field | DocType |
Automatic speech recognition,Hidden Markov models,Deep learning,Feature learning,Artificial neural networks,Convolution neural networks,Hybrid HMM/ANN | Speech processing,Pattern recognition,Convolutional neural network,Computer science,Speech recognition,Feature extraction,Time delay neural network,Artificial intelligence,Deep learning,Hidden Markov model,Speech production,Acoustic model | Journal |
Volume | ISSN | Citations |
108 | 0167-6393 | 1 |
PageRank | References | Authors |
0.43 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dimitri Palaz | 1 | 47 | 4.93 |
Mathew Magimai-Doss | 2 | 516 | 54.76 |
Ronan Collobert | 3 | 4002 | 308.61 |