Abstract | ||
---|---|---|
End-to-end models (or sequence-to-sequence models) based on deep neural networks have recently become popular within the machine learning community. These techniques are also increasingly used in automatic speech recognition as an alternative to the state-of-the-art, hybrid HMM-DNN (hidden Markov model, deep neural network) system. The end-to-end systems contain a purely neural architecture that e... |
Year | DOI | Venue |
---|---|---|
2017 | 10.1147/JRD.2017.2701207 | IBM Journal of Research and Development |
Keywords | Field | DocType |
Hidden Markov models,Acoustics,Decoding,Training,Recurrent neural networks,Mathematical model | Feature vector,Computer science,Recurrent neural network,Speech recognition,Natural language processing,Amharic,Artificial intelligence,Pashto,Hidden Markov model,Artificial neural network,Hybrid system,Connectionism | Journal |
Volume | Issue | ISSN |
61 | 4/5 | 0018-8646 |
Citations | PageRank | References |
0 | 0.34 | 10 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kartik Audhkhasi | 1 | 189 | 23.25 |
Andrew Rosenberg | 2 | 12 | 2.53 |
George Saon | 3 | 825 | 80.99 |
Abhinav Sethy | 4 | 363 | 31.16 |
Bhuvana Ramabhadran | 5 | 1779 | 153.83 |
Stanley F. Chen | 6 | 1723 | 219.64 |
Michael Picheny | 7 | 1461 | 920.15 |