41st IEEE International Conference on Acoustics, Speech and Signal Processing

March 20th 2016 - March 25th 2016

Shanghai International Convention Center - Shanghai, CHINA

Event Website
Committee Webpage
Venue Website

Presentations

Tuesday 22 March 2016

13:30 - 15:30 | Poster Area I

Audio Word Similarity for Clustering with Zero Resources Based on Iterative HMM Classification
Amélie Royer • Guillaume Gravier • Vincent Claveau

13:30 - 15:30 | Poster Area I

Convolutional Neural Network Pre-Trained with Projection Matrices on Linear Discriminant Analysis
Osamu Ichikawa • Ryuki Tachibana • Takashi Fukuda

13:30 - 15:30 | Poster Area I

Acoustic Data-Driven Pronunciation Lexicon Generation for Logographic Languages
Daniel Povey • Guoguo Chen • Sanjeev Khudanpur

13:30 - 15:30 | Poster Area H

Context Adaptive Deep Neural Networks for Fast Acoustic Model Adaptation In Noisy Conditions
Atsunori Ogawa • Chengzhu Yu • Keisuke Kinoshita • Marc Delcroix • Takuya Yoshioka • Tomohiro Nakatani

13:30 - 15:30 | Poster Area H

Speaker-Aware Training of LSTM-RNNS for Acoustic Modelling
Dong Yu • Khe Chai Sim • Liang Lu • Souvik Kundu • Tian Tan • Xiong Xiao • Yanmin Qian • Yu Zhang

13:30 - 15:30 | Poster Area H

Non-Negative Intermediate-Layer DNN Adaptation for A 10-Kb Speaker Adaptation Profile
Chaojun Liu • Kshitiz Kumar • Yifan Gong

13:30 - 15:30 | Poster Area H

DNN Speaker Adaptation Using Parameterised Sigmoid and ReLU Hidden Activation Functions
Chao Zhang • Philip Woodland

13:30 - 15:30 | Poster Area H

Speaker Adaptation of RNN-BLSTM for Speech Recognition Based on Speaker Code
Jian Tang • Li-Rong Dai • Shaofei Xue • Zhiying Huang

13:30 - 15:30 | Poster Area H

Efficient Non-Linear Feature Adaptation Using Maxout Networks
Steven Rennie • Vaibhava Goel • Xiaodong Cui

13:30 - 15:30 | Poster Area H

Sequence Summarizing Neural Network for Speaker Adaptation
Jan Cernocky • Karel Vesely • Katerina Zmolikova • Lukas Burget • Martin Karafiat • Shinji Watanabe

13:30 - 13:50 | Room 3B

The Intrinsic Value of HFO Features As A Biomarker of Epileptic Activity
Alfred Hero • Kevin Moon • Stephen V. Gliske • William C. Stacey

13:30 - 15:30 | Poster Area A

Mobile Real-time Tracking of Speakers’ Emotions, States, and Traits
Björn Schuller • Erik Marchi

13:30 - 15:30 | Poster Area A

Real-time Action Recognition via Fusion of Depth and Inertial Data
Chen Chen • Nasser Kehtarnavaz • Roozbeh Jafari

13:30 - 15:30 | Poster Area A

FluencePRO Sound Source Tracking and ECNS
Erik Visser • Lae-Hoon Kim

13:30 - 15:30 | Poster Area A

Sub-Nyquist Cognitive Radio System
Deborah Cohen • Yonina Eldar

13:30 - 15:30 | Poster Area A

A Sub-Nyquist UWB Communication System Demo
Yonina Eldar

13:30 - 15:30 | Poster Area A

Real-time Voice Conversion with Phonetic Posteriorgrams
Helen Meng • Lifa Sun • Shiyin Kang