Technical Program

Click the link to find the list of accepted papers.

Summary of the Program

Notations in the table:

• SPE: Special Session
• L: Oral Session
• P: Poster Session
• EX: Exhibition Session
• SC: Steering Committee
• ICH: International Conference Hall
• CLR: Conference Lecture Room
• CPA: Conference Poster Area

Summary of the Sessions

Tutorials and Plenaries

• Tutorial 1: Looking into the past: Power spectral representation of periodic signals, sampling theories and fundamental frequency estimation for remaking speech
• Tutorial 2: A Tutorial on How to Construct and Improve Automatic Pronunciation Proficiency Evaluation System —— take PSC test as an example
• Plenary 1: Speech-To-Speech Translation Technologies for Real-World Applications
• Plenary 2: What can speech researchers bring to music processing?
• Plenary 3: Speech and search: bridging the gap
• Plenary 4: Towards Robust Speech Recognition: Structured Modeling, Irrelevant Variability Normalization and Unsupervised Online Adaptation

Special Sessions

• SPE1 Frontiers of HMM-based TTS
• SPE2 Computer-Assisted Language Learning

Lecture Sessions

• L1 Robust Speech Recognition
• L2 Speaker and Language Recognition
• L3 Spoken Language Systems
• L4 Speech Analysis and Phonetics
• L5 Speech Synthesis
• L6 Speech Recognition

Poster Sessions

• P1 Speech Applications
• P2 Speech Recognition
• P3 Speaker Recognition
• P4 Spoken Language Processing
• P5 Speech Processing

TUTORIALS

Tutorial 1 (13:30-15:30 Dec 16)
Looking into the past: Power spectral representation of periodic signals, sampling theories and fundamental frequency estimation for remaking speech
Hideki Kawahara
Wakayama University

Tutorial 2 (16:00-18:00 Dec 16)
A Tutorial on How to Construct and Improve Automatic Pronunciation Proficiency Evaluation System —— take PSC test as an example
Yu Hu, Si Wei and Guoping Hu
iFLYTEK

PLENARY TALKS

Plenary 1 (10:00-11:00 Dec 17)
Speech-To-Speech Translation Technologies for Real-World Applications
Yuqing Gao
J. Watson Research Center

Plenary 2 (11:00-12:00 Dec 17)
What Can Speech Researchers Bring to Music Processing?
Shigeki Sagayama
University of Tokyo

Plenary 3 (8:30-9:30 Dec 18)
Speech and Search: Bridging The Gap
Vincent Vanhoucke
Google411

Plenary 4 (8:30-9:30 Dec 19)
Towards Robust Speech Recognition: Structured Modeling, Irrelevant Variability Normalization and Unsupervised Online Adaptation
Qiang Huo
Microsoft Research Asia

SPECIAL SESSIONS

SPE1 Frontiers of HMM-based TTS
Time: 13:30-15:30 Dec 17

SPE1.1 - Simultaneous Phrasing, Prosody, and Acoustic Model Training for Text-to-Speech Conversion
Author(s): Keiichiro Oura, Yoshihiko Nankaku, Tomoki Toda, Keiichi Tokuda, Rannierry Maia, Shinsuke Sakai and Satoshi Nakamura

SPE1.2 - Cross-Stream Dependency Modeling for HMM-based Speech Synthesis
Author(s): Zhen-Hua Ling, Wei Zhang and Ren-Hua Wang

SPE1.3 - Cross-Lingual Speaker Adaptation for HMM-based Speech Synthesis
Author(s): Yi-Jian Wu, Simon King and Keiichi Tokuda

SPE1.4 - HMM-Based Mixed-Language (Mandarin-English) Speech Synthesis
Author(s): Yao Qian, Hou-Wei Cao and Frank K. Soong

SPE1.5 - Improving HMM-based Speech Synthesis by Reducing Over-smoothing Problems
Author(s): Meng Zhang, Jian-Hua Tao, Hui-Bin Jia and Xia Wang

SPE2 Computer-Assisted Language Learning
Time: 13:30-15:30 Dec 18

SPE2.1 - Pronunciation Space Models for Pronunciation Evaluation
Author(s): Si Wei, Yi-Qian Pan, Guo-Ping Hu, Yu Hu and Ren-Hua Wang

SPE2.2 - Decision Fusion for Improving Mispronunciation Detection Using Language Transfer Knowledge and Phoneme-dependent Pronunciation Scoring
Author(s): W. K. Lo, Alissa M. Harrison, Helen Meng and Lan Wang

SPE2.3 - Mandarin Learning Using Speech and Language Technologies: A Translation Game in The Travel Domain
Author(s): Yu-Shi Xu and Stephanie Seneff

SPE2.4 - Word Order Correction for Language Transfer Using Relative Position Language Modeling
Author(s): Chao-Hong Liu, Chung-Hsien Wu and Matthew Harris

SPE2.5 - Improving Automatic Evaluation of Mandarin Pronunciation with Speaker Adaptive Training (Sat) and MLLR Speaker Adaption
Author(s): Chao Huang, Feng Zhang and Frank K. Soong

SPE2.6 - Automatic Assessment of Language Proficiency Through Shadowing
Author(s): Dean Luo, Nobuaki Minematsu, Yutaka Yamauchi and Keikichi Hirose

LECTURE SESSIONS

L1 Robust Speech Recognition
Time: 13:30-15:30 Dec 17

L1.1 - Improvements on Mel-frequency Cepstrum Minimum-mean-square-error Noise Suppressor for Robust Speech Recognition
Author(s): Dong Yu, Li Deng, Jian Wu, Yi-Fan Gong and Alex Acero

L1.2 - Effect of Feature Smoothing for Robust Speech Recognition
Author(s): Xiong Xiao, Eng Siong Chng and Hai-Zhou Li

L1.3 - Reference Eigen-environment and Speaker Weighting for Robust Speech Recognition
Author(s): Yuan-Fu Liao, Hung-Hsiang Fang and Chih-Min Yang

L1.4 - Evaluation of A Feature Compensation Approach Using High-order Vector Taylor Series Approximation of An Explicit Distortion Model on Aurora2, Aurora3, and Aurora4 Tasks
Author(s): Jun Du, Qiang Huo and Yu Hu

L1.5 - Deriving MFCC Parameters from The Dynamic Spectrum for Robust Speech Recognition
Author(s): Neng-Heng Zheng, Xia Li, Hou-Wei Cao, Tan Lee and P. C. Ching

L1.6 - Discriminative Output Coding Features for Speech Recognition
Author(s): Omid Dehzangi, Bin Ma, Eng Siong Chng and Hai-Zhou Li

L2 Speaker and Language Recognition
Time: 16:00-18:00 Dec 17

L2.1 - Double Gauss Based Unsupervised Score Normalization in Speaker Verification
Author(s): Wu Guo, Li-Rong Dai and Ren-Hua Wang

L2.2 - Discriminative Feedback Adaptation for GMM-UBM Speaker Verification
Author(s): Yi-Hsiang Chao, Wei-Ho Tsai and Hsin-Min Wang

L2.3 - Using Pseudo-key for Language Recogition System Design
Author(s): Han-Wu Sun, Bin Ma and Hai-Zhou Li

L2.4 - Self-organized Clustering for Feature Mapping in Language Recognition
Author(s): Chang-Huai You, Kong-Aik Lee, Bin Ma and Hai-Zhou Li

L2.5 - An Efficient Feature Selection Method for Speaker Recognition
Author(s): Han-Wu Sun, Bin Ma and Hai-Zhou Li

L2.6 - PLSA Based Topic Mixture Language Modeling Approach
Author(s): Shuan-Hu Bai and Hai-Zhou Li

L3 Spoken Language Systems
Time: 10:00-12:00 Dec 18

L3.1 - The Improved TS-base Approaches with Interference Compensation and Their Evaluations for Speech Enhancement
Author(s): Jun-Feng Li, Shuichi Sakamoto, Satoshi Hongo, Masato Akagi and Yoiti Suzuki

L3.2 - Pitch Tracking for Model-based Speech Separation
Author(s): S. W. Lee, Frank K. Soong, P. C. Ching and Tan Lee

L3.3 - Improved Linear Discriminant Analysis Considering Empirical Pairwise Classification Error Rates
Author(s): Hung-Shin Lee and Berlin Chen

L3.4 - Citybrowser II: A Multimodal Restaurant Guide in Mandarin
Author(s): Jing-Jing Liu, Yu-Shi Xu, Stephanie Seneff and Victor Zue

L3.5 - Evaluation and Analysis of Minimum Phone Error Training and Its Modified Versions for Large Vocabulary Mandarin Speech Recognition
Author(s): Yung-Jen Cheng, Che-Kuang Lin and Lin-Shan Lee

L3.6 - A Two-stage Algorithm for Multi-speaker Identification System
Author(s): Yong Guan and Wen-Ju Liu

L4 Speech Analysis and Phonetics
Time: 16:00-18:00 Dec 18

L4.1 - What’s in The F0 of Mandarin Speech--Tones, Intonation and Beyond
Author(s): Chiu-Yu Tseng and Zhao-Yu Su

L4.2 - A Perceptual Study of Approximated Cantonese Tone Contours
Author(s): Yu-Jia Li and Tan Lee

L4.3 - A New Prosodic Strength Calculation Method for Prosody Reduction Modeling
Author(s): Hong-Lei Cong, Zhi-Yong Wu, Lian-Hong Cai and Helen M. Meng

L4.4 - Prosody Study with Context-dependent Acoustic Models
Author(s): Yue-Ning Hu and Min Chu

L4.5 - Intonational Prominence of “SHI…(DE)” Construction in Standard Chinese
Author(s): Yuan Jia, Ai-Jun Li and Zi-Yu Xiong

L4.6 - Entropy-based Analysis of The Prosodic Features of Chinese Dialects
Author(s): Raymond W. M. Ng and Tan Lee

L5 Speech Synthesis
Time: 10:00-12:00 Dec 19

L5.1 - Frequency Modulation Technique for Prosodic Modification
Author(s): Jin-Fu Ni, Shinsuke Sakai, Tohru Shimizu and Satoshi Nakamura

L5.2 - Modeling and Generating Tone Contour with Phrase Intonation for Chinese Mandarin Speech
Author(s): Zhizheng Wu, Yao Qian and Frank K. Soong

L5.3 - A Three-stage Text Normalization Strategy For Mandarin Text-to-speech Systems
Author(s): Tao Zhou, Yuan Dong, De-zhi Huang, Wu Liu and Hai-la Wang

L5.4 - Multi-Layer F0 Modeling For HMM-Based Speech Synthesis
Author(s): Cheng-Cheng Wang, Zhen-Hua Ling, Bu-Fan Zhang and Li-Rong Dai

L5.5 - Predicting Spectral and Prosodic Parameters for Unit Selection in Speech Synthesis
Author(s): Ming-Hui Dong and Hai-Zhou Li

L5.6 - Heteronym Verification for Mandarin Speech Synthesis
Author(s): Heng Lu, Zhen-Hua Ling, Si Wei, Yu Hu, Li-Rong Dai and Ren-Hua Wang

L6 Speech Recognition
Time: 13:30-15:30 Dec 19

L6.1 - Investigation on Adaptation Using Different Discriminative Training Criteria Based Linear Regression and Map
Author(s): Bo Zhu, Zhi-Jie Yan, Yu Hu, Zhi-Guo Wang, Li-Rong Dai and Ren-Hua Wang

L6.2 - Utilization of Huge Written Text Corpora for Conversational Speech Recognition
Author(s): Xin-Hui Hu, Hirofumi Yamamoto, Jin-Song Zhang, Keiji Yasuda, You-Zheng Wu and Hideki Kashioka

L6.3 - Position Information for Language Modeling in Speech Recognition
Author(s): Hsuan-Sheng Chiu, Guan-Yu Chen, Chun-Jen Lee and Berlin Chen

L6.4 - An Investigation of Phonological Feature Systems Used in Detection-based ASR
Author(s): I-Fan Chen and Hsin-Min Wang

L6.5 - An HMM Compensatioon Approach for Dynamic Features Using Unscented Transformation and Its Application to Noisy Speech Recognition
Author(s): Yu Hu and Qiang Huo

L6.6 - Mandarin Language Understanding in Dialogue Context
Author(s): Yu-Shi Xu, Jing-Jing Liu and Stephanie Seneff

POSTER SESSIONS

P1 Speech Applications
Time: 10:00-12:00 Dec 18

P1.1 - Pronunciation Error Detection for Computer Assisted Pronunciation Teaching in Mandarin
Author(s): Min-siong Liang, Ren-Yuan Lyu, Yuang-Chin Chiang and Jing-Fung Chen

P1.2 - A Two-stage Multi-feature Integration Approach to Unsupervised Speaker Change Detection in Real-time News Broadcasting
Author(s): Lei Xie and Guang-Sen Wang

P1.3 - Automatic Prosody Boundary Labeling of Mandarin Using Both Text and Acoustic Information
Author(s): Chong-Jia Ni, Wen-Ju Liu and Bo Xu

P1.4 - Subword Latent Semantic Analysis for TextTiling-based Automatic Story Segmentation of Chinese Broadcast News
Author(s): Yu-Lian Yang, Lei Xie

P1.5 - Multipitch Detection Based on Weighted Summary Correlogram
Author(s): Xue-Liang Zhang, Wen-Ju liu, Peng Li and Bo Xu

P1.6 - Efficient System Combination for Syllable-confusion-network-based Chinese Spoken Term Detection
Author(s): Jie Gao, Jian Shao, Qing-Wei Zhao and Yong-Hong Yan

P1.7 - The Use of Dynamic Deformable Templates for Lip Tracking in An Audio-visual Corpus with Large Variations in Head Pose, Face Illumination and Lip Shapes
Author(s): Zhi-Yong Wu, Ji-Ying Wu and Helen M. Meng

P1.8 - Microphone Array Post-filter Based on Auditory Filtering
Author(s): Peng Li, Feng-Chai Liao, Ning Cheng, Bo Xu and Wen-Ju Liu

P1.9 - Exploring Tone Variations in Chinese Dialects Using Context Dependent Tone Models
Author(s): Wei Guo and Min Chu

P2 Speech Recognition
Time: 13:30-15:30 Dec 18

P2.1 - A Trellis Based Fast Lattice Generating Algorithm
Author(s): Wei Li, Ji Wu and Zhi-Guo Wang

P2.2 - Order Adaptation of The Fractional Fourier Transform Using The Intraframe Pitch Change Rate for Speech Recognition
Author(s): Hui Yin, Climent Nadeu, Volker Hohmann, Xiang Xie and Jing-Ming Kuang

P2.3 - Large Vocabulary Continuous Speech Recognition in Uyghur: Data Preparation and Experimental Results
Author(s): Nasirjan Tursun and Wushour Silamu

P2.4 - A Improvement for Training Efficiency of Semi-tied Covariance
Author(s): Si-Bao Chen, Yu Hu, Bin Luo and Ren-Hua Wang

P2.5 - Improved Semi-parametric Mean Trajectory Model Using Discriminatively Trained Centroids
Author(s): Ran Xu, Jie-Lin Pan and Yong-Hong Yan

P2.6 - Local Mismatch Phone for Confidence Measure in Standard and Accented Chinese Speech Recognition
Author(s): Wen-Xiao Cao, Yi Liu and Fang Zheng

P2.7 - A Combined Task Analysis Method for Data Selection in Mandarin Isolated Word Recognition System
Author(s): Zhi-Yang He, Zhi-Guo Wang, Wei Li and Ji Wu

P2.8 - Mandarin Speech Recognition For Nonnative Speakers Based on Pronunciation Dictionary Adaption
Author(s): Jian Yang, Pei-Shan Wu and Dan Xu

P2.9 - A New Similarity Measure Between HMMs
Author(s): Yih-Ru Wang

P2.10 - Recognition of Syllable-contracted Words in Spontaneous Speech Using Word Expansion and Duration Information
Author(s): Wei-Bin Liang, Chung-Hsien Wu and Yu-Kai Kang

P2.11 - Exploiting Non-target Region Information for Confidence Measure Based on Bayesian Information Criterion
Author(s): Cong Liu, Yu Hu, Xiong-Guo Lei, Zhi-Guo Wang, Li-Rong Dai and Ren-Hua Wang

P3 Speaker Recognition
Time:16:00-18:00 Dec 18

P3.1 -Simplified Deformation Compensation for Emotional Speaker Recognition
Author(s):Ying-Chun Yang, Tian Wu and Hong-Bin Lv

P3.2 - Interfusing The Confused Region Score of Speaker Verification Systems
Author(s): Yan-Hua Long, Wu Guo and Li-Rong Dai

P3.3 - Parallel Phone Recognizer Based MLLR Speaker Recognition
Author(s): Eryu Wang, Wu Guo and Li-Rong Dai

P3.4 - Eigenchannel Compensation and Symmetric Score for A Robust Text-independent Speaker Verification
Author(s): Yuan Dong, Jian Zhao, Xian-Yu Zhao, Liang Lu, Ji-Qing Liu and Hai-La Wang

P3.5 - A Sample and Feature Selection Scheme for Gmm-svm Based Language Recognition
Author(s): Yan Song and Li-Rong Dai

P3.6 - Speaker Recognition Using A Kind of Novel Phonotactic Information
Author(s): Xiang Zhang, Xiang Xiao, Hai-Peng Wang, Hong-Bin Suo, Qing-Wei Zhao and Yong-Hong Yan

P3.7 - The Adaptation Schemes in PR-SVM Based Language Recognition
Author(s): Bing Xu, Yan Song and Li-Rong Dai

P3.8 - Mandarin Tone Perception with Temporal Envelope and Periodicity Cues from Different Frequency Regions
Author(s): Meng Yuan, Tan Lee and Sigfrid D. Soli

P3.9 - Prosodic Variation in Cantonese-english Code-mixed Speech
Author(s): Wen-Tao Gu, Tan Lee and P. C. Ching

P4 Spoken Language Processing
Time: 10:00-12:00 Dec 19

P4.1 - Word Alignment Based on Multi-grain Model
Author(s): Yan-Qing He, Yu Zhou and Cheng-Qing Zong

P4.2 - Word Reordering Alignment for Combination of Statistical Machine Translation Systems
Author(s): Mao-Xi Li and Cheng-Qing Zong

P4.3 - An EMD Based Approach to Transliteration Unit Alignment Between English and Chinese
Author(s): Mu-Yun Yang, Shu-Jie Liu, Sheng Li, Ju-Feng Li, Tie-Jun Zhao and Hao-Liang Qi

P4.4 - Analysis and Modeling of Affective Audio Visual Speech Based on Pad Emotion Space
Author(s): Shen Zhang, Ying-Jin Xu, Jia Jia and Lian-Hong Cai

P4.5 - Noise Reduction Based Random Matrix Theory
Author(s): XU-Gang Lu, S. Matsuda, T. Shimizu and S. Nakamura

P4.6 - Language Model Adaptation for Relevance Feedback in Information Retrieval
Author(s): Ying-Lang Chang and Jen-Tzung Chien

P4.7 - Predicting and Tagging Dialog-act Using MDP and SVM
Author(s): Ke-Yan Zhou, Cheng-Qing Zong, Hua Wu and Hai-Feng Wang

P4.8 - A Synchronous Method for Automatic Scoring of Language Learning
Author(s): Bin Dong and Yong-Hong Yan

P4.9 - Using Reference to Tune Language Model for Detection of Reading Miscues
Author(s): Chang-Liang Liu, Fu-Ping Pan, Feng-Pei Ge, Bin Dong and Yong-Hong Yan

P4.10 - How Syllables Group in Chinese
Author(s): Mao-Lin Wang and Yi Xu

P5 Speech Processing
Time: 13:30-15:30 Dec 19

P5.1 - Prosodic Modeling for Isolated Mandarin Words and Its Application
Author(s): Hung-Kuang Shih, Chen-Yu Chiang, Yih-Ru Wang and Sin-Horng Chen

P5.2 - A CSI and Rate-Distortion Based Packet Loss Recovery Algorithm for VoIP
Author(s): Zhong-Bo Li, Sheng-Hui Zhao, Jing Wang and Jing-Ming Kuang

P5.3 - Mandarin Stops Classification Based on Random Forest Approach
Author(s): Chi-Yueh Lin and Hsiao-Chuan Wang

P5.4 - A Pitch Synchronous Method for Speech Modification
Author(s): Chih-Ting Kuo and Hsiao-Chuan Wang

P5.5 - Speech Database Compacted for An Embedded Mandarin TTS System
Author(s): Qing Guo, Bin Wang and Nobuyuki Katae

P5.6 - Prosody Modification on Mixed-language Speech Synthesis
Author(s): Yi Zhang and Jian-Hua Tao

P5.7 - A Maximum Entropy Based Hierarchical Model for Automatic Prosodic Boundary Labeling in Mandarin
Author(s): Fang-Zhou Liu, Hui-Bin Jia and Jian-Hua Tao

P5.8 - Tone Evaluation of Chinese Continuous Speech Based on Prosodic Words
Author(s): Yi-Qian Pan, Si Wei and Ren-Hua Wang

P5.9 - The Pitch Analysis of Imperative Sentences in Standard Chinese
Author(s): Jia Sun, Ji-Lun Lu, Ai-Jun Li and Yuan Jia