Technical Program
SP-L3: Acoustic Modeling with Neural Networks |
| Session Type: Lecture |
| Time: Wednesday, May 29, 08:00 - 10:00 |
| Location: Room 211 |
| Session Chair: Brian Kingsbury, IBM |
| SP-L3.1: DEEP NEURAL NETWORK FEATURES AND SEMI-SUPERVISED TRAINING FOR LOW RESOURCE SPEECH RECOGNITION |
| Samuel Thomas; The Johns Hopkins University |
| Michael Seltzer; Microsoft Research |
| Kenneth Church; IBM Research |
| Hynek Hermansky; The Johns Hopkins University |
| SP-L3.2: INVESTIGATING DEEP NEURAL NETWORK BASED TRANSFORMS OF ROBUST AUDIO FEATURES FOR LVCSR |
| Enrico Bocchieri; AT&T Labs Research |
| Dimitrios Dimitriadis; AT&T Labs Research |
| SP-L3.3: FEATURE COMBINATION AND STACKING OF RECURRENT AND NON-RECURRENT NEURAL NETWORKS FOR LVCSR |
| Christian Plahl; RWTH Aachen University |
| Michał Kozielski; RWTH Aachen University |
| Ralf Schlüter; RWTH Aachen University |
| Hermann Ney; RWTH Aachen University |
| SP-L3.4: MLP-BASED FACTOR ANALYSIS FOR TANDEM SPEECH RECOGNITION |
| Marc Ferras; Idiap Research Institute |
| Hervé Bourlard; Idiap Research Institute |
| SP-L3.5: AN EMPIRICAL STUDY OF LEARNING RATES IN DEEP NEURAL NETWORKS FOR SPEECH RECOGNITION |
| Andrew Senior; Google Inc. |
| Georg Heigold; Google Inc. |
| Marc'Aurelio Ranzato; Google Inc. |
| Ke Yang; Google Inc. |
| SP-L3.6: GAUSSIAN-BERNOULLI RESTRICTED BOLTZMANN MACHINES AND AUTOMATIC FEATURE EXTRACTION FOR NOISE ROBUST MISSING DATA MASK ESTIMATION |
| Sami Keronen; Aalto University School of Science |
| KyungHyun Cho; Aalto University School of Science |
| Tapani Raiko; Aalto University School of Science |
| Alexander Ilin; Aalto University School of Science |
| Kalle Palomäki; Aalto University School of Science |