ASR-3: Speech Recognition 3 and Synthesis |
| Session Type: Poster |
| Poster Time: Friday, December 16, 10:30 - 12:30 |
| Location: Lahaina Bay Room |
| Session Chair: Pedro Moreno, Google Inc. |
| ASR-3.1: CODE-SWITCHING DETECTION USING MULTILINGUAL DNNS |
| Emre Yilmaz; Radboud University Nijmegen, Netherlands |
| Henk Van den Heuvel; Radboud University Nijmegen, Netherlands |
| David Van Leeuwen; Radboud University Nijmegen, Netherlands |
| ASR-3.2: ATTRIBUTE BASED SHARED HIDDEN LAYERS FOR CROSS-LANGUAGE KNOWLEDGE TRANSFER |
| Vipul Arora; University of Oxford, United Kingdom |
| Aditi Lahiri; University of Oxford, United Kingdom |
| Henning Reetz; Goethe University, Germany |
| ASR-3.3: TOWARDS ACOUSTIC MODEL UNIFICATION ACROSS DIALECTS |
| Mohamed Elfeky; Google Inc., United States |
| Meysam Bastani; Google Inc., United States |
| Xavier Velez; Google Inc., United States |
| Pedro Moreno; Google Inc., United States |
| Austin Waters; Google Inc., United States |
| ASR-3.4: BOOSTING PERFORMANCE ON LOW-RESOURCE LANGUAGES BY STANDARD CORPORA: AN ANALYSIS |
| František Grézl; Brno University of Technology, Czech Republic |
| Martin Karafiat; Brno University of Technology, Czech Republic |
| ASR-3.5: MULTILINGUAL BLSTM AND SPEAKER-SPECIFIC VECTOR ADAPTATION IN 2016 BUT BABEL SYSTEM |
| Martin Karafiat; Speech@FIT VUT, Czech Republic |
| Murali Karthick Baskar; Speech@FIT VUT, Czech Republic |
| Pavel Matějka; Speech@FIT VUT, Czech Republic |
| Karel Vesely; Speech@FIT VUT, Czech Republic |
| František Grézl; Speech@FIT VUT, Czech Republic |
| Jan Černocký; Speech@FIT VUT, Czech Republic |
| ASR-3.6: DNN ADAPTATION FOR RECOGNITION OF CHILDREN SPEECH THROUGH AUTOMATIC UTTERANCE SELECTION |
| Marco Matassoni; Fondazione Bruno Kessler, Italy |
| Daniele Falavigna; Fondazione Bruno Kessler, Italy |
| Diego Giuliani; Fondazione Bruno Kessler, Italy |
| ASR-3.7: LOW-RANK BASES FOR FACTORIZED HIDDEN LAYER ADAPTATION OF DNN ACOUSTIC MODELS |
| Lahiru Samarakoon; National University of Singapore, Singapore |
| Khe Chai Sim; Google Inc., United States |
| ASR-3.8: DEEP NEURAL NETWORK BASED ACOUSTIC MODEL PARAMETER REDUCTION USING MANIFOLD REGULARIZED LOW RANK MATRIX FACTORIZATION |
| Hoon Chung; Electronics and Telecommunications Research Institute, Republic of Korea |
| Jeom Ja Kang; Electronics and Telecommunications Research Institute, Republic of Korea |
| Ki Young Park; Electronics and Telecommunications Research Institute, Republic of Korea |
| Sung Joo Lee; Electronics and Telecommunications Research Institute, Republic of Korea |
| Jeon Gue Park; Electronics and Telecommunications Research Institute, Republic of Korea |
| ASR-3.9: AUTOMATED STRUCTURE DISCOVERY AND PARAMETER TUNING OF NEURAL NETWORK LANGUAGE MODEL BASED ON EVOLUTION STRATEGY |
| Tomohiro Tanaka; Tokyo Institute of Technology, Japan |
| Takafumi Moriya; NTT Corporation, Japan |
| Takahiro Shinozaki; Tokyo Institute of Technology, Japan |
| Shinji Watanabe; Mitsubishi Electric Research Laboratories, United States |
| Takaaki Hori; Mitsubishi Electric Research Laboratories, United States |
| Kevin Duh; Johns Hopkins University, United States |
| ASR-3.10: ENTROPY-BASED PRUNING OF HIDDEN UNITS TO REDUCE DNN PARAMETERS |
| Gautam Mantena; National University of Singapore, Singapore |
| Khe Chai Sim; Google Inc., United States |
| ASR-3.11: INFLUENCE OF CORPUS SIZE AND CONTENT ON THE PERCEPTUAL QUALITY OF A UNIT SELECTION MARYTTS VOICE |
| Florian Hinterleitner; TU Berlin, Germany |
| Benjamin Weiss; TU Berlin, Germany |
| Sebastian Möller; TU Berlin, Germany |
| ASR-3.12: MEDIAN-BASED GENERATION OF SYNTHETIC SPEECH DURATIONS USING A NON-PARAMETRIC APPROACH |
| Srikanth Ronanki; University of Edinburgh, United Kingdom |
| Oliver Watts; University of Edinburgh, United Kingdom |
| Simon King; University of Edinburgh, United Kingdom |
| Gustav Henter; University of Edinburgh, United Kingdom |
| ASR-3.13: F0 TRANSFORMATION TECHNIQUES FOR STATISTICAL VOICE CONVERSION WITH DIRECT WAVEFORM MODIFICATION WITH SPECTRAL DIFFERENTIAL |
| Kazuhiro Kobayashi; Nara Institute of Science and Technology, Japan |
| Tomoki Toda; Nagoya University, Japan |
| Satoshi Nakamura; Nara Institute of Science and Technology, Japan |
