SPE-89.4
UNSUPERVISED DATA SELECTION FOR SPEECH RECOGNITION WITH CONTRASTIVE LOSS RATIOS
Chanho Park, Rehan Ahmad, Thomas Hain, The University of Sheffield, United Kingdom of Great Britain and Northern Ireland
Session:
Augmentation for Speech Recognition
Track:
Speech and Language Processing
Location:
Gather Area C
Presentation Time:
Fri, 13 May, 23:00 - 23:45 China Time (UTC +8)
Fri, 13 May, 15:00 - 15:45 UTC
Fri, 13 May, 15:00 - 15:45 UTC
Session Chair:
Yao Qian, Microsoft
Session SPE-89
SPE-89.1: PHONE-INFORMED REFINEMENT OF SYNTHESIZED MEL SPECTROGRAM FOR DATA AUGMENTATION IN SPEECH RECOGNITION
Sei Ueno, Tatsuya Kawahara, Graduate School of Informatics, Kyoto University, Japan
SPE-89.2: LPC AUGMENT: AN LPC-BASED ASR DATA AUGMENTATION ALGORITHM FOR LOW AND ZERO-RESOURCE CHILDREN’S DIALECTS
Alexander Johnson, Ruchao Fan, Abeer Alwan, University of California - Los Angeles, United States of America; Robin Morris, Georgia State University, United States of America
SPE-89.3: TOWARDS BETTER META-INITIALIZATION WITH TASK AUGMENTATION FOR KINDERGARTEN-AGED SPEECH RECOGNITION
Yunzheng Zhu, Ruchao Fan, Abeer Alwan, University of California, Los Angeles, United States of America
SPE-89.4: UNSUPERVISED DATA SELECTION FOR SPEECH RECOGNITION WITH CONTRASTIVE LOSS RATIOS
Chanho Park, Rehan Ahmad, Thomas Hain, The University of Sheffield, United Kingdom of Great Britain and Northern Ireland
SPE-89.5: IMPORTANTAUG: A DATA AUGMENTATION AGENT FOR SPEECH
Viet Anh Trinh, Hassan Kavaki, The City University of New York, United States of America; Michael Mandel, Brooklyn College, United States of America
SPE-89.6: INJECTING TEXT AND CROSS-LINGUAL SUPERVISION IN FEW-SHOT LEARNING FROM SELF-SUPERVISED MODELS
Matthew Wiesner, Human Language Technology Center of Excellence, United States of America; Desh Raj, Sanjeev Khudanpur, Johns Hopkins University, United States of America