SPE-31: Speech Recognition 11: Novel Approaches |
Session Type: Poster |
Time: Thursday, 10 June, 13:00 - 13:45 |
Location: Gather.Town |
Virtual Session: View on Virtual Platform |
Session Chair: Jinyu Li, Microsoft |
SPE-31.1: MINIMUM BAYES RISK TRAINING FOR END-TO-END SPEAKER-ATTRIBUTED ASR |
Naoyuki Kanda; Microsoft |
Zhong Meng; Microsoft |
Liang Lu; Microsoft |
Yashesh Gaur; Microsoft |
Xiaofei Wang; Microsoft |
Zhuo Chen; Microsoft |
Takuya Yoshioka; Microsoft |
SPE-31.2: MUTUALLY-CONSTRAINED MONOTONIC MULTIHEAD ATTENTION FOR ONLINE ASR |
Jaeyun Song; Korea Advanced Institute of Science and Technology (KAIST) |
Hajin Shim; Korea Advanced Institute of Science and Technology (KAIST) |
Eunho Yang; Korea Advanced Institute of Science and Technology (KAIST) |
SPE-31.3: THE USE OF VOICE SOURCE FEATURES FOR SUNG SPEECH RECOGNITION |
Gerardo Roa Dabike; University of Sheffield |
Jon Barker; University of Sheffield |
SPE-31.4: A PARALLELIZABLE LATTICE RESCORING STRATEGY WITH NEURAL LANGUAGE MODELS |
Ke Li; Johns Hopkins University |
Daniel Povey; Xiaomi Corp. |
Sanjeev Khudanpur; Johns Hopkins University |
SPE-31.5: DECENTRALIZING FEATURE EXTRACTION WITH QUANTUM CONVOLUTIONAL NEURAL NETWORK FOR AUTOMATIC SPEECH RECOGNITION |
Chao-Han Huck Yang; Georgia Institute of Technology |
Jun Qi; Georgia Institute of Technology |
Pin-Yu Chen; IBM Research |
Yen-Chi Samuel Chen; Brookhaven National Laboratory |
Sabato Marco Siniscalchi; University of Enna |
Xiaoli Ma; Brookhaven National Laboratory |
Chin-Hui Lee; Georgia Institute of Technology |
SPE-31.6: CIF-BASED COLLABORATIVE DECODING FOR END-TO-END CONTEXTUAL SPEECH RECOGNITION |
Minglun Han; Institute of Automation, Chinese Academy of Sciences |
Linhao Dong; Institute of Automation, Chinese Academy of Sciences |
Shiyu Zhou; Institute of Automation, Chinese Academy of Sciences |
Bo Xu; Institute of Automation, Chinese Academy of Sciences |