SLP-L17.5

DISTILLING DISTRIBUTIONAL UNCERTAINTY FROM A GAUSSIAN PROCESS

Jeremy Heng Meng Wong, Nancy F. Chen, Institute for Infocomm Research, Singapore

Session:
SLP-L17: Speech analysis - Pitch, Spectrum and Voice disorders Lecture

Track:
Speech and Language Processing

Location:
Room E8

Presentation Time:
Wed, 17 Apr, 17:50 - 18:10 (UTC +9)

Session Co-Chairs:
Yu Tsao, Academia Sinica and Ehsan Variani, Google
View Manuscript
Presentation
Discussion
Resources
Session SLP-L17
SLP-L17.1: High-Fidelity and Pitch-Controllable Neural Vocoder Based on Unified Source-Filter Networks
Reo Yoneyama, Nagoya University, Japan; Yi-Chiao Wu, Tomoki Toda, Meta Reality Labs Research Scientist, United States of America
SLP-L17.2: AUTOMATIC TEMPORAL ALIGNMENT FOR PITCH ESTIMATION EVALUATION
Desheng Wang, Jing Wang, Hao Zheng, Yanbin Hou, Shenyang University of Technology, China
SLP-L17.3: HAFFORMER: A HIERARCHICAL ATTENTION-FREE FRAMEWORK FOR ALZHEIMER’S DISEASE DETECTION FROM SPONTANEOUS SPEECH
Zhongren Dong, Zixing Zhang, Weixiang Xu, Hunan University, China; Jing Han, University of Cambridge, United Kingdom of Great Britain and Northern Ireland; Jianjun Ou, Central South University, China; Björn W. Schuller, Imperial College London, United Kingdom of Great Britain and Northern Ireland
SLP-L17.4: NOISE-ROBUST DSP-ASSISTED NEURAL PITCH ESTIMATION WITH VERY LOW COMPLEXITY
Krishna Subramani, University of Illinois at Urbana-Champaign, United States of America; Jean-Marc Valin, Jan Büthe, Paris Smaragdis, Mike Goodwin, Amazon, Canada
SLP-L17.5: DISTILLING DISTRIBUTIONAL UNCERTAINTY FROM A GAUSSIAN PROCESS
Jeremy Heng Meng Wong, Nancy F. Chen, Institute for Infocomm Research, Singapore
SLP-L17.6: COVID-19 Detection via Fusion of Modulation Spectrum and Linear Prediction Speech Features
Yi Zhu, INRS, Canada; Abhishek Tiwari, Myant Inc., Canada; João Monteiro, ServiceNow Research, Canada; Shruti Kshirsagar, Wichita State University, Canada; Tiago Falk, INRS, Canada
Contacts