AUD-36.6
RECONSTRUCTING SPEECH FROM CNN EMBEDDINGS
Luca Comanducci, Paolo Bestagini, Augusto Sarti, Stefano Tubaro, Politecnico di Milano, Italy; Marco Tagliasacchi, Google Research, Italy
Session:
Topics in Convolutional and Latent Variable Modeling
Track:
Audio and Acoustic Signal Processing
Location:
Gather Area L
Presentation Time:
Fri, 13 May, 22:00 - 22:45 China Time (UTC +8)
Fri, 13 May, 14:00 - 14:45 UTC
Fri, 13 May, 14:00 - 14:45 UTC
Session Chair:
Bhan Lam, Nanyang Technological University
Presentation
Discussion
Resources
No resources available.
Session AUD-36
AUD-36.1: ATTENTIVE MAX FEATURE MAP AND JOINT TRAINING FOR ACOUSTIC SCENE CLASSIFICATION
Hye-jin Shim, Ju-ho Kim, Ha-Jin Yu, University of Seoul, Korea, Republic of; Jee-weon Jung, Naver corporation, Korea, Republic of
AUD-36.2: A Variational Bayesian Approach to Learning Latent Variables for Acoustic Knowledge Transfer
Hu Hu, Chao-Han Huck Yang, Chin-Hui Lee, Georgia Institute of Technology, United States of America; Sabato Marco Siniscalchi, University of Enna Kore, Italy
AUD-36.3: PSLA: IMPROVING AUDIO TAGGING WITH PRETRAINING, SAMPLING, LABELING, AND AGGREGATION
Yuan Gong, Yu-An Chung, James Glass, Massachusetts Institute of Technology, United States of America
AUD-36.4: EXPLOITING TEMPORAL CONTEXT IN CNN BASED MULTISOURCE DOA ESTIMATION
Alexander Bohlender, Nilesh Madhu, Ghent University – imec, Belgium; Ann Spriet, Wouter Tirry, Goodix Technology (Belgium) B.V., Belgium
AUD-36.5: ORCA-PARTY: AN AUTOMATIC KILLER WHALE SOUND TYPE SEPARATION TOOLKIT USING DEEP LEARNING
Christian Bergler, Manuel Schmitt, Andreas Maier, Elmar Nöth, Friedrich-Alexander-University Erlangen-Nuremberg, Germany; Rachael Xi Cheng, Leibniz Institute for Zoo and Wildlife Research, Germany; Volker Barth, Anthro-Media, Germany
AUD-36.6: RECONSTRUCTING SPEECH FROM CNN EMBEDDINGS
Luca Comanducci, Paolo Bestagini, Augusto Sarti, Stefano Tubaro, Politecnico di Milano, Italy; Marco Tagliasacchi, Google Research, Italy