Microsoft at Interspeech 2019

Monday, September 16

15:30-15:50 | Hall 1 | Oral
Speaker Adaptation for Attention-Based End-to-End Speech Recognition
Zhong Meng (opens in new tab), Yashesh Gaur (opens in new tab), Jinyu Li, Yifan Gong (opens in new tab)

14:30-16:30 | Gallery C | Poster
Zero Shot Intent Classification Using Long-Short Term Memory Networks
Kyle Williams

14:30 – 16:30 | Hall 4 | Show & Tell
Speech Based Web Navigation for Movement Impaired Users
Vasiliy Radostev (opens in new tab), Serge Berger (opens in new tab), Justin Tabrizi (opens in new tab), Pasha Kamyshev (opens in new tab), Hisami Suzuki (opens in new tab)

Tuesday, September 17

10:00-12:00 | Hall 10/E | Poster
A Scalable Noisy Speech Dataset and Online Subjective Test Framework 
Ebrahim Beyrami (opens in new tab), Chandan Karadagur Ananda Reddy (opens in new tab), Jamie Pool (opens in new tab), Ross Cutler (opens in new tab), Sriram Srinivasan (opens in new tab), Johannes Gehrke

13:30-15:30 | Hall 10/E | Poster
Speech Signal Characterization 3/Vocal Pitch Extraction in Polyphonic Music using Convolutional Residual Network
Mingye Dong, Jie Wu (opens in new tab), Jian Luan (opens in new tab)

13:30-13:50 | Hall 1 | Oral
Forward-Backward Decoding for Regularizing End-to-End TTS
Yibin Zheng, Xi Wang (opens in new tab), Lei He (opens in new tab), Shifeng Pan (opens in new tab), Frank Soong, Zhengqi Wen, Jianhua Tao (opens in new tab)

13:50-14:10 | Hall 2 | Oral
A New GAN-based End-to-End TTS Training Algorithm 
Haohan Guo, Frank Soong, Lei He (opens in new tab), Lei Xie

14:10-14:30 | Hall 2 | Oral
Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTS
Mutian He, Yan Deng (opens in new tab), Lei He (opens in new tab)

16:00-18:00 | Gallery A | Poster
Token-Level Ensemble Distillation for Grapheme-to-Phoneme Conversion 
Hao Sun, Xu Tan, Jun-Wei Gan (opens in new tab), Hongzhi Liu, Sheng Zhao (opens in new tab), Tao Qin (opens in new tab), Tie-Yan Liu

16:00-18:00 | Gallery B | Poster
Exploiting Monolingual Speech Corpora for Code-mixed Speech Recognition
Karan Taneja, Satarupa Guha (opens in new tab), Preethi Jyothi, Basil Abraham (opens in new tab)

16:40-17:00 | Hall 1 | Oral
Layer Trajectory BLSTM
Eric Sun, Jinyu Li, Yifan Gong (opens in new tab)

16:00-18:00 | Gallery C | Poster
Acoustic-to-Phrase Models for Speech Recognition 
Yashesh Gaur (opens in new tab), Jinyu Li, Zhong Meng (opens in new tab), Yifan Gong (opens in new tab)

Wednesday, September 18

11:20-11:40 | Hall 1 | Oral
Supervised Classifiers for Audio Impairments with Noisy Labels 
Chandan Karadagur Ananda Reddy (opens in new tab), Ross Cutler (opens in new tab), Johannes Gehrke

10:00-12:00 | Gallery B | Poster
Meeting Transcription Using Asynchronous Distant Microphones
Takuya Yoshioka, Dimitrios Dimitriadis, Andreas Stolcke, William Hinthorn, Zhuo Chen (opens in new tab), Michael Zeng, Xuedong Huang

13:30-15:30 | Gallery B | Poster
Compression of CTC-Trained Acoustic Models by Dynamic Frame-Wise Distillation or Segment-Wise N-Best Hypotheses Imitation
Haisong Ding, Kai Chen, Qiang Huo

13:30-15:30 | Gallery B | Poster
Latent Dirichlet Allocation based Acoustic Data Selection for Automatic Speech Recognition
Mortaza (Morrie) Doulaty (opens in new tab), Thomas Hain

17:40-18:00 | Hall 1| Oral
Self-Teaching Networks 
Liang Lu (opens in new tab), Eric Sun, Yifan Gong (opens in new tab)

16:00-18:00 | Hall 10/E | Poster
Sound Event Detection in Multichannel Audio Using Convolutional Time-Frequency Channel Squeeze and Excitation
Wei Xia, Kazuhito Koishida

Thursday, September 19

13:30-15:30 | Gallery C | Poster
Exploiting Syntactic
Features in a Parsed Tree to Improve End-to-End TTS 
Haohan Guo, Frank Soong, Lei He (opens in new tab), Lei Xie

13:30-15:30 | Hall 12 | Special Session
Speech Technologies for Code-Switching in Multilingual Communities
Organizers: Kalika Bali, Alan W Black, Julia Hirschberg, Sunayana Sitaram, Thamar SolorioOpens in a new tab