Technical Program
SP-L1: Neural Network Trends in Speech Recognition |
| Session Type: Lecture |
| Time: Tuesday, March 22, 13:30 - 15:30 |
| Location: Yangtse River Hall (5F) |
| Session Chairs: Bhuvana Ramabhadran, IBM Watson and Michiel Bacchiani, Google Inc. |
| SP-L1.1: EXPLORING MULTIDIMENSIONAL LSTMS FOR LARGE VOCABULARY ASR |
| Jinyu Li; Microsoft Corporation |
| Abdelrahman Mohamed; Microsoft Corporation |
| Geoffrey Zweig; Microsoft Corporation |
| Yifan Gong; Microsoft Corporation |
| SP-L1.2: END-TO-END ATTENTION-BASED LARGE VOCABULARY SPEECH RECOGNITION |
| Dzmitry Bahdanau; Université de Montréal |
| Jan Chorowski; University of Wrocław |
| Dmitriy Serdyuk; Université de Montréal |
| Philémon Brakel; Université de Montréal |
| Yoshua Bengio; Université de Montréal |
| SP-L1.3: DEEP CONVOLUTIONAL ACOUSTIC WORD EMBEDDINGS USING WORD-PAIR SIDE INFORMATION |
| Herman Kamper; University of Edinburgh |
| Weiran Wang; Toyota Technological Institute at Chicago |
| Karen Livescu; Toyota Technological Institute at Chicago |
| SP-L1.4: VERY DEEP MULTILINGUAL CONVOLUTIONAL NEURAL NETWORKS FOR LVCSR |
| Tom Sercu; IBM |
| Christian Puhrsch; New York University |
| Brian Kingsbury; IBM |
| Yann LeCun; New York University |
| SP-L1.5: LISTEN, ATTEND AND SPELL: A NEURAL NETWORK FOR LARGE VOCABULARY CONVERSATIONAL SPEECH RECOGNITION |
| William Chan; Carnegie Mellon University |
| Navdeep Jaitly; Google Inc. |
| Quoc Le; Google Inc. |
| Oriol Vinyals; Google Inc. |
| SP-L1.6: A DEEP SCATTERING SPECTRUM - DEEP SIAMESE NETWORK PIPELINE FOR UNSUPERVISED ACOUSTIC MODELING |
| Neil Zeghidour; Ecole des Hautes Etudes en Sciences Sociales |
| Gabriel Synnaeve; Facebook A.I. Research |
| Maarten Versteegh; École normale supérieure |
| Emmanuel Dupoux; Ecole des Hautes Etudes en Sciences Sociales |
ICASSP 2016 Patrons
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |