Technical Program
SP-P6: Topics in Speech Recognition |
| Session Type: Poster |
| Time: Tuesday, March 7, 16:00 - 18:00 |
| Location: Churchill: Poster Area A |
| Session Chair: Preethi Jyothi, Indian Institute of Technology, Bombay |
| SP-P6.1: AN EMPIRICAL EVALUATION OF ZERO RESOURCE ACOUSTIC UNIT DISCOVERY |
| Chunxi Liu; Johns Hopkins University |
| Jinyi Yang; University of Chinese Academy of Sciences |
| Ming Sun; Amazon |
| Santosh Kesiraju; International Institute of Information Technology |
| Alena Rott; Stanford University |
| Lucas Ondel; Brno University of Technology |
| Pegah Ghahremani; Johns Hopkins University |
| Najim Dehak; Johns Hopkins University |
| Lukas Burget; Brno University of Technology |
| Sanjeev Khudanpur; Johns Hopkins University |
| SP-P6.2: STATISTICAL NORMALISATION OF PHASE-BASED FEATURE REPRESENTATION FOR ROBUST SPEECH RECOGNITION |
| Erfan Loweimi; The University of Sheffield |
| Jon Barker; The University of Sheffield |
| Thomas Hain; The University of Sheffield |
| SP-P6.3: ACTIVE LEARNING FOR LOW-RESOURCE SPEECH RECOGNITION: IMPACT OF SELECTION SIZE AND LANGUAGE MODELING DATA |
| Ali Syed; The Graduate Center, CUNY |
| Andrew Rosenberg; IBM T.J. Watson Research Center |
| Michael Mandel; The Graduate Center, CUNY |
| SP-P6.4: MICROPHONE ARRAY PROCESSING STRATEGIES FOR DISTANT BASED AUTOMATIC SPEECH RECOGNITION |
| John H.L. Hansen; The University of Texas at Dallas |
| Soudeh A. Khoubrouy; The University of Texas at Dallas |
| SP-P6.5: IMPROVING AUDIO-VISUAL SPEECH RECOGNITION USING DEEP NEURAL NETWORKS WITH DYNAMIC STREAM RELIABILITY ESTIMATES |
| Hendrik Meutzner; Ruhr-Universität Bochum |
| Ning Ma; University of Sheffield |
| Robert Nickel; Bucknell University |
| Christopher Schymura; Ruhr-Universität Bochum |
| Dorothea Kolossa; Ruhr-Universität Bochum |
| SP-P6.6: BEAMNET: END-TO-END TRAINING OF A BEAMFORMER-SUPPORTED MULTI-CHANNEL ASR SYSTEM |
| Jahn Heymann; Paderborn University |
| Lukas Drude; Paderborn University |
| Christoph Boeddeker; Paderborn University |
| Patrick Hanebrink; Paderborn University |
| Reinhold Haeb-Umbach; Paderborn University |
| SP-P6.7: PREDICTING ERROR RATES FOR UNKNOWN DATA IN AUTOMATIC SPEECH RECOGNITION |
| Bernd T. Meyer; Johns Hopkins University |
| Sri Harish Mallidi; Johns Hopkins University |
| Hendrik Kayser; Carl von Ossietzky Universität Oldenburg |
| Hynek Hermansky; Johns Hopkins University |
| SP-P6.8: SPEEDING UP SOFTMAX COMPUTATIONS IN DNN-BASED LARGE VOCABULARY SPEECH RECOGNITION BY SENONE WEIGHT VECTOR SELECTION |
| Yingke Zhu; The Hong Kong University of Science & Technology |
| Brian Mak; The Hong Kong University of Science & Technology |
| SP-P6.9: IMPROVING LATENCY-CONTROLLED BLSTM ACOUSTIC MODELS FOR ONLINE SPEECH RECOGNITION |
| Shaofei Xue; Alibaba Inc |
| Zhijie Yan; Alibaba Inc |
| SP-P6.10: RETURNN: THE RWTH EXTENSIBLE TRAINING FRAMEWORK FOR UNIVERSAL RECURRENT NEURAL NETWORKS |
| Patrick Doetsch; RWTH Aachen University |
| Albert Zeyer; RWTH Aachen University |
| Paul Voigtlaender; RWTH Aachen University |
| Ilia Kulikov; RWTH Aachen University |
| Ralf Schlüter; RWTH Aachen University |
| Hermann Ney; RWTH Aachen University |