MLSP-1.3
EXPLOITING HYBRID MODELS OF TENSOR-TRAIN NETWORKS FOR SPOKEN COMMAND RECOGNITION
Jun Qi, Georgia Institute of Technology, United States of America; Javier Tejedor, Universidad San Pablo-CEU, CEU Universities, Spain
Session:
Deep Learning for Audio and Music Applications
Track:
Machine Learning for Signal Processing
Location:
Gather Area F
Presentation Time:
Sun, 8 May, 20:00 - 20:45 China Time (UTC +8)
Sun, 8 May, 12:00 - 12:45 UTC
Sun, 8 May, 12:00 - 12:45 UTC
Session Chair:
Jianwu Dang, Japan Advanced Institute of Science and Technology
Session MLSP-1
MLSP-1.1: DIRECT DESIGN OF BIQUAD FILTER CASCADES WITH DEEP LEARNING BY SAMPLING RANDOM POLYNOMIALS
Joseph Colonel, Christian Steinmetz, Joshua Reiss, Queen Mary University of London, United Kingdom of Great Britain and Northern Ireland; Marcus Michelen, University of Illinois at Chicago, United States of America
MLSP-1.2: AN END-TO-END DEEP LEARNING SPEECH CODING AND DENOISING STRATEGY FOR COCHLEAR IMPLANTS
Tom Gajecki, Waldo Nogueira, Hannover Medical School, Germany
MLSP-1.3: EXPLOITING HYBRID MODELS OF TENSOR-TRAIN NETWORKS FOR SPOKEN COMMAND RECOGNITION
Jun Qi, Georgia Institute of Technology, United States of America; Javier Tejedor, Universidad San Pablo-CEU, CEU Universities, Spain
MLSP-1.4: Learnable Wavelet Packet Transform for Data-Adapted Spectrograms
Gaëtan Frusque, Olga Fink, ETH Zürich, Switzerland
MLSP-1.5: MUSIC ENHANCEMENT VIA IMAGE TRANSLATION AND VOCODING
Nikhil Kandpal, University of North Carolina at Chapel Hill, United States of America; Oriol Nieto, Zeyu Jin, Adobe, United States of America
MLSP-1.6: PROGRESSIVE TEACHER-STUDENT TRAINING FRAMEWORK FOR MUSIC TAGGING
Rui Lu, Baigong Zheng, Jiarui Hai, Fei Tao, Zhiyao Duan, Ji Liu, Kuaishou Technology, China