2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
SPE-21: Speech Recognition 7: Training Methods for End-to-End Modeling |
| Session Type: Poster |
| Time: Wednesday, 9 June, 15:30 - 16:15 |
| Location: Gather.Town |
| Virtual Session: View on Virtual Platform |
| Session Chair: Karen Livescu, TTI-Chicago |
| SPE-21.1: TOP-DOWN ATTENTION IN END-TO-END SPOKEN LANGUAGE UNDERSTANDING |
| Yixin Chen; University of California, Los Angeles |
| Weiyi Lu; Amazon Alexa |
| Alejandro Mottini; Amazon Alexa |
| Li Erran Li; Amazon Alexa |
| Jasha Droppo; Amazon Alexa |
| Zheng Du; Amazon Alexa |
| Belinda Zeng; Amazon Alexa |
| SPE-21.2: FINE-TUNING OF PRE-TRAINED END-TO-END SPEECH RECOGNITION WITH GENERATIVE ADVERSARIAL NETWORKS |
| Md. Akmal Haidar; Huawei Noah's Ark Lab |
| Mehdi Rezagholizadeh; Huawei Noah's Ark Lab |
| SPE-21.3: A GENERAL MULTI-TASK LEARNING FRAMEWORK TO LEVERAGE TEXT DATA FOR SPEECH TO TEXT TASKS |
| Yun Tang; Facebook |
| Juan Pino; Facebook |
| Changhan Wang; Facebook |
| Xutai Ma; Johns Hopkins University |
| Dmitriy Genzel; Facebook |
| SPE-21.4: GAUSSIAN KERNELIZED SELF-ATTENTION FOR LONG SEQUENCE DATA AND ITS APPLICATION TO CTC-BASED SPEECH RECOGNITION |
| Yosuke Kashiwagi; Sony Corporation |
| Emiru Tsunoo; Sony Corporation |
| Shinji Watanabe; Johns Hopkins University |
| SPE-21.5: LATTICE-FREE MMI ADAPTATION OF SELF-SUPERVISED PRETRAINED ACOUSTIC MODELS |
| Apoorv Vyas; Idiap Research Institute and EPFL |
| Srikanth Madikeri; Idiap Research Institute |
| Hervé Bourlard; Idiap Research Institute |
| SPE-21.6: INTERMEDIATE LOSS REGULARIZATION FOR CTC-BASED SPEECH RECOGNITION |
| Jaesong Lee; Naver Corporation |
| Shinji Watanabe; Johns Hopkins University |