SLP-L2: End-to-end Speech Recognition II: New Models |
Session Type: Lecture |
Time: Tuesday, May 14, 17:30 - 19:30 |
Location: Auditorium 1 |
Session Chairs: Jinyu Li, Microsoft and Yanzhang He, Google Inc.
|
|
SLP-L2.1: A SPELLING CORRECTION MODEL FOR END-TO-END SPEECH RECOGNITION |
Jinxi Guo; University of California, Los Angeles |
Tara N. Sainath; Google, Inc. |
Ron J. Weiss; Google, Inc. |
|
SLP-L2.2: SELF-ATTENTION ALIGNER: A LATENCY-CONTROL END-TO-END MODEL FOR ASR USING SELF-ATTENTION NETWORK AND CHUNK-HOPPING |
Linhao Dong; Institute of Automation, Chinese Academy of Sciences |
Feng Wang; Institute of Automation, Chinese Academy of Sciences |
Bo Xu; Institute of Automation, Chinese Academy of Sciences |
|
SLP-L2.3: LARGE CONTEXT END-TO-END AUTOMATIC SPEECH RECOGNITION VIA EXTENSION OF HIERARCHICAL RECURRENT ENCODER-DECODER MODELS |
Ryo Masumura; NTT Corporation |
Tomohiro Tanaka; NTT Corporation |
Takafumi Moriya; NTT Corporation |
Yusuke Shinohara; NTT Corporation |
Takanobu Oba; NTT Corporation |
Yushi Aono; NTT Corporation |
|
SLP-L2.4: TRIGGERED ATTENTION FOR END-TO-END SPEECH RECOGNITION |
Niko Moritz; Mitsubishi Electric Research Laboratories |
Takaaki Hori; Mitsubishi Electric Research Laboratories |
Jonathan Le Roux; Mitsubishi Electric Research Laboratories |
|
SLP-L2.5: ON USING 2D SEQUENCE-TO-SEQUENCE MODELS FOR SPEECH RECOGNITION |
Parnia Bahar; RWTH Aachen University |
Albert Zeyer; RWTH Aachen University |
Ralf Schlüter; RWTH Aachen University |
Hermann Ney; RWTH Aachen University |
|
SLP-L2.6: CRF-BASED SINGLE-STAGE ACOUSTIC MODELING WITH CTC TOPOLOGY |
Hongyu Xiang; Tsinghua University |
Zhijian Ou; Tsinghua University |
|