ASR II |
| Session Type: Poster |
| Time: Thursday, December 20, 13:30 - 15:30 |
| Location: Kallirhoe Hall |
| OCCAM'S ADAPTATION: A COMPARISON OF INTERPOLATION OF BASES ADAPTATION METHODS FOR MULTI-DIALECT ACOUSTIC MODELING WITH LSTMS |
| Mikaela Grace; Google |
| Meysam Bastani; Google |
| Eugene Weinstein; Google |
| SPEECH CHAIN FOR SEMI-SUPERVISED LEARNING OF JAPANESE-ENGLISH CODE-SWITCHING ASR AND TTS |
| Sahoko Nakayama; Nara Institute of Science and Technology |
| Andros Tjandra; Nara Institute of Science and Technology |
| Sakriani Sakti; Nara Institute of Science and Technology |
| Satoshi Nakamura; Nara Institute of Science and Technology |
| IMPROVING ASR ERROR DETECTION WITH RNNLM ADAPTATION |
| Rahhal Errattahi; University of Chouaib Doukkali |
| Salil Deena; The University of Sheffield |
| Asmaa El Hannani; University of Chouaib Doukkali |
| Hassan Ouahmane; University of Chouaib Doukkali |
| Thomas Hain; The University of Sheffield |
| MULTI-OBJECTIVE MULTI-TASK LEARNING ON RNNLM FOR SPEECH RECOGNITION |
| Minguang Song; University of Missouri |
| Yunxin Zhao; University of Missouri |
| Shaojun Wang; Ping An Technology |
| CONFIDENCE ESTIMATION AND DELETION PREDICTION USING BIDIRECTIONAL RECURRENT NEURAL NETWORKS |
| Anton Ragni; University of Cambridge |
| Qiujia Li; University of Cambridge |
| Mark Gales; University of Cambridge |
| Yu Wang; University of Cambridge |
| IMPROVING OOV DETECTION AND RESOLUTION WITH EXTERNAL LANGUAGE MODELS IN ACOUSTIC-TO-WORD ASR |
| Hirofumi Inaguma; Kyoto University |
| Masato Mimura; Kyoto University |
| Shinsuke Sakai; Kyoto University |
| Tatsuya Kawahara; Kyoto University |
| LSTM LANGUAGE MODEL ADAPTATION WITH IMAGES AND TITLES FOR MULTIMEDIA AUTOMATIC SPEECH RECOGNITION |
| Yasufumi Moriya; Dublin City University |
| Gareth Jones; Dublin City University |
| FIRST-PASS TECHNIQUES FOR VERY LARGE VOCABULARY SPEECH RECOGNITION OF MORPHOLOGICALLY RICH LANGUAGES |
| Matti Varjokallio; Aalto University |
| Sami Virpioja; Aalto University |
| Mikko Kurimo; Aalto University |
| ANALYZING DEEP CNN-BASED UTTERANCE EMBEDDINGS FOR ACOUSTIC MODEL ADAPTATION |
| Joanna Rownicka; The University of Edinburgh |
| Peter Bell; The University of Edinburgh |
| Steve Renals; The University of Edinburgh |
| MULTI-BAND PROCESSING WITH GABOR FILTERS AND TIME DELAY NEURAL NETS FOR NOISE ROBUST SPEECH RECOGNITION |
| György Kovács; MTA-SZTE Research Group on Artificial Intelligence |
| László Tóth; University of Szeged |
| Gábor Gosztolya; MTA-SZTE Research Group on Artificial Intelligence |
| A TEACHER-STUDENT LEARNING APPROACH FOR UNSUPERVISED DOMAIN ADAPTATION OF SEQUENCE-TRAINED ASR MODELS |
| Vimal Manohar; Johns Hopkins University |
| Pegah Ghahremani; Johns Hopkins University |
| Daniel Povey; Johns Hopkins University |
| Sanjeev Khudanpur; Johns Hopkins University |
| DOMAIN ROBUST FEATURE EXTRACTION FOR RAPID LOW RESOURCE ASR DEVELOPMENT |
| Siddharth Dalmia; Carnegie Mellon University |
| Xinjian Li; Carnegie Mellon University |
| Florian Metze; Carnegie Mellon University |
| Alan W Black; Carnegie Mellon University |