Technical Program
SP-L2: End to End Speech Processing |
| Session Type: Lecture |
| Time: Monday, March 6, 16:00 - 18:00 |
| Location: Grand Ballroom |
| Session Chairs: Bhuvana Ramabhadran, IBM T.J. Watson Research and Jinyu Li, MSFT |
| SP-L2.1: JOINT CTC-ATTENTION BASED END-TO-END SPEECH RECOGNITION USING MULTI-TASK LEARNING |
| Suyoun Kim; Carnegie Mellon University |
| Takaaki Hori; Mitsubishi Electric Research Laboratories |
| Shinji Watanabe; Mitsubishi Electric Research Laboratories |
| SP-L2.2: END-TO-END ASR-FREE KEYWORD SEARCH FROM SPEECH |
| Kartik Audhkhasi; IBM |
| Andrew Rosenberg; IBM |
| Abhinav Sethy; IBM |
| Bhuvana Ramabhadran; IBM |
| Brian Kingsbury; IBM |
| SP-L2.3: VERY DEEP CONVOLUTIONAL NETWORKS FOR END-TO-END SPEECH RECOGNITION |
| Yu Zhang; Massachusetts Institute of Technology |
| William Chan; Carnegie Mellon University |
| Navdeep Jaitly; Google Brain |
| SP-L2.4: CONFIDENCE MEASURES FOR CTC-BASED PHONE SYNCHRONOUS DECODING |
| Zhehuai Chen; Shanghai Jiao Tong University |
| Yimeng Zhuang; Shanghai Jiao Tong University |
| Kai Yu; Shanghai Jiao Tong University |
| SP-L2.5: MINIMUM BAYES RISK TRAINING OF CTC ACOUSTIC MODELS IN MAXIMUM A POSTERIORI BASED DECODING FRAMEWORK |
| Naoyuki Kanda; National Institute of Information and Communications Technology |
| Xugang Lu; National Institute of Information and Communications Technology |
| Hisashi Kawai; National Institute of Information and Communications Technology |
| SP-L2.6: END-TO-END SPOOFING DETECTION WITH RAW WAVEFORM CLDNNS |
| Heinrich Dinkel; Shanghai Jiao Tong University |
| Nanxin Chen; Shanghai Jiao Tong University |
| Yanmin Qian; Shanghai Jiao Tong University |
| Kai Yu; Shanghai Jiao Tong University |