{"id":578437,"date":"2019-04-11T08:55:08","date_gmt":"2019-04-11T15:55:08","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-event&p=578437"},"modified":"2025-08-06T11:56:30","modified_gmt":"2025-08-06T18:56:30","slug":"icassp-2019","status":"publish","type":"msr-event","link":"https:\/\/www.microsoft.com\/en-us\/research\/event\/icassp-2019\/","title":{"rendered":"Microsoft @ ICASSP 2019"},"content":{"rendered":"\n\n

Venue:<\/strong> Brighton Conference Centre (opens in new tab)<\/span><\/a><\/p>\n

Website:<\/strong> ICASSP 2019 (opens in new tab)<\/span><\/a>Opens in a new tab<\/span><\/p>\n

Microsoft is excited to be a Silver sponsor of the 44th<\/sup> International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (opens in new tab)<\/span><\/a> May 12 \u2013 17, 2019, in Brighton, UK. Stop by our booth to chat with our experts, see demos of our latest research and find out more about career opportunities with Microsoft.<\/p>\n

Session chairs<\/h3>\n

Frank K. Soong<\/a>
\nIvan Tashev<\/a>
\nJinyu Li<\/a>
\nDavid Wipf<\/a><\/p>\n

Microsoft attendees<\/h3>\n

Amy Siebenthaler
\nAndreas Stolcke<\/a>
\nAnthony Stark
\nDimitra Emmanouilidou<\/a>
\nDimitrios Dimitriadis<\/a>
\nEric Sun
\nFei Zuo
\nFrank K. Soong<\/a>
\nHamid Palangi<\/a>
\nHannes Gamper<\/a>
\nIvan Tashev<\/a>
\nJack Stokes
\nJian Wu
\nJianfeng Gao<\/a>
\nJinyu Li<\/a>
\nKazuhito Koishida<\/a>
\nKshitiz Kumar
\nLei He
\nMichael Levit<\/a>
\nMortaza Doulaty
\nNanshan Zeng
\nNikunj Raghuvanshi<\/a>
\nOren Barkan
\nSarangarajan Parthasarathy<\/a>
\nSebastian Braun<\/a>
\nShifeng Pan
\nShuayb Zarar<\/a>
\nSungjin Lee<\/a>
\nTasos Anastasakos
\nXiaoyang Chen
\nXuedong Huang<\/a>
\nYan Huang<\/a>
\nYao Tian
\nYashesh Gaur
\nYifan Gong
\nYong Zhao<\/p>\n

 Opens in a new tab<\/span><\/p>\n

A Pitch-Aware Approach to Single-Channel Speech Separation<\/strong>
\nTuesday, May 14, 2019 | 1:30 PM\u20133:30 PM | Music Source Separation and Spatial Audio | Poster Area E<\/p>\n

Ke Wang, Frank Soong<\/a>, Lei Xie<\/p>\n

A Sparsity Measure for Echo Density Growth in General Environments<\/strong>
\nTuesday, May 14, 2019 | 1:30 PM\u20133:30 PM | Acoustic Environments and Music Analysis | Poster Area D<\/p>\n

Helena Peic Tukuljac, Ville Pulkki, Hannes Gamper<\/a>, Keith Godin<\/strong>, Ivan Tashev<\/a>, Nikunj Raghuvanshi<\/a><\/p>\n

Blind Room Volume Estimation from Single-Channel Noisy Speech<\/strong>
\nTuesday, May 14, 2019 | 1:30 PM\u20133:30 PM | Acoustic Environments and Music Analysis | Poster Area D<\/p>\n

Andrea Genovese, Hannes Gamper<\/a>, Ville Pulkki, Nikunj Raghuvanshi<\/a>, Ivan Tashev<\/a><\/p>\n

Improving Binaural Ambisonics Decoding by Spherical Harmonics Domain Tapering and Coloration Compensation<\/strong>
\nTuesday, May 14, 2019 | 1:30 PM\u20133:30 PM | Music Source Separation and Spatial Audio | Poster Area E<\/p>\n

Christoph Hold, Hannes Gamper<\/a>, Ville Pulkki, Nikunj Raghuvanshi<\/a>, Ivan Tashev<\/a><\/p>\n

Static and Dynamic State Predictions for Acoustic Model Combination<\/strong>
\nTuesday, May 14, 2019 | 1:30 PM\u20133:30 PM | Deep Learning Applications I | Auditorium 2<\/p>\n

Kshitiz Kumar<\/strong>, Yifan Gong <\/strong><\/p>\n

\n

Gaussian Process LSTM Recurrent Neural Network Language Models for Speech Recognition<\/strong>
\nTuesday, May 14, 2019 | 5:30 PM\u20137:30 PM | Language Modeling, ASR and Punctuation Prediction | Poster Area C<\/p>\n

Max W.Y. Lam, Xie Chen<\/a>, Shoukang Hu, Jianwei Yu, Xunying Liu, Helen Meng<\/p>\n

Investigation of Sampling Techniques for Maximum Entropy Language Modeling Training<\/strong>
\nTuesday, May 14, 2019 | 5:30 PM\u20137:30 PM | Language Modeling, ASR and Punctuation Prediction | Poster Area C<\/p>\n

Xie Chen<\/a>, Jun Zhang<\/strong>, Tasos Anastasakos<\/strong>, Fil Alleva<\/p>\n

Recurrent Neural Network Language Model Training Using Natural Gradient<\/strong>
\nTuesday, May 14, 2019 | 5:30 PM\u20137:30 PM | Language Modeling, ASR and Punctuation Prediction | Poster Area C<\/p>\n

Jianwei Yu, Max W.Y. Lam, Xie Chen<\/a>, Shoukang Hu, Songxiang Liu, Xixin Wu, Xunying Liu, Helen Meng<\/p>\n

Towards Code-Switching ASR for End-to-End CTC Models<\/strong>
\nTuesday, May 14, 2019 | 5:30 PM\u20137:30 PM | Multi-lingual Speech Recognition | Poster Area A<\/p>\n

Ke Li, Jinyu Li<\/a>, Guoli Ye<\/strong>, Rui Zhao<\/strong>, Yifan Gong<\/strong><\/p>\n

\n

Adversarial Speaker Verification<\/strong>
\nWednesday, May 15, 2019 | 8:30 AM\u201310:30 AM | Features and Robustness for Speaker Identification | Poster Area B<\/p>\n

Zhong Meng<\/strong>, Yong Zhao<\/strong>, Jinyu Li<\/a>, Yifan Gong<\/strong><\/p>\n

Attention in Recurrent Neural Networks for Ransomware Detection<\/strong>
\nWednesday, May 15, 2019 | 8:30 AM\u201310:30 AM | Deep Learning III | Poster Area G<\/p>\n

Rakshit Agrawal, Jack W. Stokes<\/a>, Karthik Selvaraj<\/strong>, Mady Marinescu<\/strong><\/p>\n

Encrypted Speech Recognition Using Deep Polynomial Networks<\/strong>
\nWednesday, May 15, 2019 | 8:30 AM\u201310:30 AM | Novel Architectures and Training Strategies for ASR | Auditorium 1<\/p>\n

Shixiong Zhang, Yifan Gong<\/strong>, Dong Yu<\/p>\n

Single-Channel Speech Extraction Using Speaker Inventory and Attention Network<\/strong>
\nWednesday, May 15, 2019 | 8:30 AM\u201310:30 AM | Source Separation and Speech Enhancement I | Meeting Room 1<\/p>\n

Xiong Xiao<\/strong>, Zhuo Chen<\/strong>, Takuya Yoshioka<\/a>, Hakan Erdogan, Changliang Liu<\/strong>, Dimitrios Dimitriadis<\/a>, Jasha Droppo, Yifan Gong<\/strong><\/p>\n

Universal Acoustic Modeling Using Neural Mixture Models<\/strong>
\nWednesday, May 15, 2019 | 8:30 AM\u201310:30 AM | Novel Architectures and Training Strategies for ASR | Auditorium 1<\/p>\n

Amit Das<\/strong>, Jinyu Li<\/a>, Changliang Liu<\/strong>, Yifan Gong<\/strong><\/p>\n

\n

Adversarial Speaker Adaptation<\/strong>
\nWednesday, May 15, 2019 | 1:30 PM\u20133:30 PM | Feature Learning and Adaptation for ASR | Auditorium 1<\/p>\n

Zhong Meng<\/strong>, Jinyu Li<\/a>, Yifan Gong<\/strong><\/p>\n

Detecting Cyber Attacks Using Anomaly Detection with Explanations and Expert Feedback<\/strong>
\nWednesday, May 15, 2019 | 1:30 PM\u20133:30 PM | Learning Theory and Methods I | Auditorium 2<\/p>\n

Md Amran Siddiqui, Jack W. Stokes<\/a>, Christian Seifert<\/strong>, Evan Argyle<\/strong>, Robert McCann<\/strong>, Joshua Neil<\/strong>, Justin Carroll<\/strong><\/p>\n

\n

Directional Interference Suppression Using a Spatial Relative Transfer Function Feature<\/strong>
\nWednesday, May 15, 2019 | 4:00 PM\u20136:00 PM | Quality Measures and Sensor Array Processing | Poster Area D<\/p>\n

Sebastian Braun<\/a>, Ivan Tashev<\/a><\/p>\n

NN-Based Ordinal Regression for Assessing Fluency of ESL Speech<\/strong>
\nWednesday, May 15, 2019 | 4:00 PM\u20136:00 PM | Training Regimes for Emotion and Sentiment Analysis | Poster Area C<\/p>\n

Shaoguang Mao, Zhiyong Wu, Jingshuai Jiang<\/strong>, Peiyun Liu<\/strong>, Frank Soong<\/a><\/p>\n

Non-Intrusive Speech Quality Assessment Using Neural Networks<\/strong><\/a>
\nWednesday, May 15, 2019 | 4:00 PM\u20136:00 PM | Quality Measures and Sensor Array Processing | Poster Area D<\/p>\n

Anderson R. Avila, Hannes Gamper<\/a>, Chandan Reddy<\/strong>, Ross Cutler<\/strong>, Ivan Tashev<\/a>, Johannes Gehrke<\/a><\/p>\n

\n

Conditional Teacher-Student Learning<\/strong>
\nThursday, May 16, 2019 | 8:00 AM\u201310:00 AM | ASR Training Strategies and Toolkits | Poster Area A<\/p>\n

Zhong Meng<\/strong>, Jinyu Li<\/a>, Yong Zhao<\/strong>, Yifan Gong<\/strong><\/p>\n

Decoding Homomorphically Encrypted Flac Audio Without Decryption<\/strong>
\nThursday, May 16, 2019 | 8:00 AM\u201310:00 AM | Audio Security and Source Separation | Poster Area D<\/p>\n

Yuanyuan Tang, Bin Zhu<\/a>, Xiaojing Ma, Mathiopoulos P. Takis, Xia Xie, Hong Huang<\/p>\n

\n

Improving Layer Trajectory LSTM with Future Context Frames<\/strong>
\nThursday, May 16, 2019 | 1:00 PM\u20133:00 PM | New Features, Models and Representations\/Audio Visual ASR | Poster Area A<\/p>\n

Jinyu Li<\/a>, Liang Lu<\/strong>, Changliang Liu<\/strong>, Yifan Gong<\/strong><\/p>\n

\n

Contextual Out-of-Domain Utterance Handling with Counterfeit Data Augmentation<\/strong><\/a>
\nThursday, May 16, 2019 | 3:30 PM\u20135:30 PM | Dialogue | Syndicate 1<\/p>\n

Sungjin Lee<\/a>, Igor Shalyminov<\/p>\n

Dilated Residual Network with Multi-Head Self-Attention for Speech Emotion Recognition<\/strong>
\nThursday, May 16, 2019 | 3:30 PM\u20135:30 PM | Architectures for Emotion and Sentiment Analysis | Poster Area B<\/p>\n

Runnan Li, Zhiyong Wu, Jia Jia, Sheng Zhao<\/strong>, Helen Meng<\/p>\n

\n

Attentive Adversarial Learning for Domain-Invariant Training<\/strong>
\nThursday, May 16, 2019 | 6:00 PM\u20138:00 PM | Robust Speech Recognition | Poster Area A<\/p>\n

Zhong Meng<\/strong>, Jinyu Li<\/a>, Yifan Gong<\/strong><\/p>\n

Speech Super Resolution Generative Adversarial Network<\/strong>
\nThursday, May 16, 2019 | 6:00 PM\u20138:00 PM | Audio and Speech Applications | Poster Area G<\/p>\n

Sefik Emre Eskimez, Kazuhito Koishida<\/a><\/p>\n

Word Characters and Phone Pronunciation Embedding for ASR Confidence Classifier<\/strong>
\nThursday, May 16, 2019 | 6:00 PM\u20138:00 PM | Signal Processing for Emerging and Practical Applications | Poster Area E<\/p>\n

Session Chair: Ivan Tashev<\/a>
\nKshitiz Kumar<\/strong>, Tasos Anastasakos<\/strong>, Yifan Gong<\/strong><\/p>\n

\n

Acoustic and Lexical Sentiment Analysis for Customer Service Calls<\/strong><\/a>
\nFriday, May 17, 2019 | 8:30 AM\u201310:30 AM | Using Multiple Perspectives in Emotion and Sentiment Analysis | Syndicate 3<\/p>\n

Bryan Li, Dimitrios Dimitriadis<\/a>, Andreas Stolcke<\/a><\/p>\n

Domain Adversarial Training for Improving Keyword Spotting Performance of ESL Speech<\/strong>
\nFriday, May 17, 2019 | 8:30 AM\u201310:30 AM | Artificial Intelligence Based Human-Machine Conversation Technology for Interactive Education | Syndicate 1<\/p>\n

Session Chairs: Yao Qian, Helen Meng, Frank K. Soong<\/a>
\nJingyong Hou, Pengcheng Guo, Sining Sun, Frank K. Soong<\/a>, Wenping Hu<\/a>, Lei Xie<\/p>\n

Learning Latent Representations for Style Control and Transfer in End-to-End Speech Synthesis<\/strong>
\nFriday, May 17, 2019 | 8:30 AM\u201310:30 AM | Speech Synthesis II | Poster Area B<\/p>\n

Ya-Jie Zhang, Shifeng Pan<\/strong>, Lei He<\/strong>, Zhen-Hua Ling<\/p>\n

\n

Low-Latency Speaker-Independent Continuous Speech Separation<\/strong>
\nFriday, May 17, 2019 | 1:30 PM\u20133:30 PM | Speech Separation, Enhancement and Denoising | Poster Area A<\/p>\n

Takuya Yoshioka<\/a>, Zhuo Chen<\/strong>, Changliang Liu<\/strong>, Xiong Xiao<\/strong>, Hakan Erdogan, Dimitrios Dimitriadis<\/a><\/p>\n

\n

Cross Modal Audio Search and Retrieval with Joint Embeddings Based on Text and Audio<\/strong>
\nFriday, May 17, 2019 | 4:00 PM\u20136:00 PM | Multimedia Analysis | Poster Area C<\/p>\n

Benjamin Elizalde, Shuayb Zarar<\/a>, Bhiksha Raj<\/p>\n

Opens in a new tab<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"

Microsoft is excited to be a Silver sponsor of the 44th International Conference on Acoustics, Speech, and Signal Processing (ICASSP) May 12 \u2013 17, 2019, in Brighton, UK.<\/p>\n","protected":false},"featured_media":581446,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr_startdate":"2019-05-12","msr_enddate":"2019-05-17","msr_location":"Brighton, United Kingdom","msr_expirationdate":"","msr_event_recording_link":"","msr_event_link":"","msr_event_link_redirect":false,"msr_event_time":"","msr_hide_region":false,"msr_private_event":false,"msr_hide_image_in_river":0,"footnotes":""},"research-area":[243062,13545],"msr-region":[239178,243014],"msr-event-type":[197941],"msr-video-type":[],"msr-locale":[268875],"msr-program-audience":[],"msr-post-option":[],"msr-impact-theme":[],"class_list":["post-578437","msr-event","type-msr-event","status-publish","has-post-thumbnail","hentry","msr-research-area-audio-acoustics","msr-research-area-human-language-technologies","msr-region-europe","msr-region-middle-east-africa","msr-event-type-conferences","msr-locale-en_us"],"msr_about":"\n\n

Venue:<\/strong> Brighton Conference Centre (opens in new tab)<\/span><\/a><\/p>\n

Website:<\/strong> ICASSP 2019 (opens in new tab)<\/span><\/a>Opens in a new tab<\/span><\/p>\n

Microsoft is excited to be a Silver sponsor of the 44th<\/sup> International Conference on Acoustics, Speech, and Signal Processing (ICASSP)<\/a> May 12 \u2013 17, 2019, in Brighton, UK. Stop by our booth to chat with our experts, see demos of our latest research and find out more about career opportunities with Microsoft.<\/p>\n

Session chairs<\/h3>\n

Frank K. Soong<\/a>
\nIvan Tashev<\/a>
\nJinyu Li<\/a>
\nDavid Wipf<\/a><\/p>\n

Microsoft attendees<\/h3>\n

Amy Siebenthaler
\nAndreas Stolcke<\/a>
\nAnthony Stark
\nDimitra Emmanouilidou<\/a>
\nDimitrios Dimitriadis<\/a>
\nEric Sun
\nFei Zuo
\nFrank K. Soong<\/a>
\nHamid Palangi<\/a>
\nHannes Gamper<\/a>
\nIvan Tashev<\/a>
\nJack Stokes
\nJian Wu
\nJianfeng Gao<\/a>
\nJinyu Li<\/a>
\nKazuhito Koishida<\/a>
\nKshitiz Kumar
\nLei He
\nMichael Levit<\/a>
\nMortaza Doulaty
\nNanshan Zeng
\nNikunj Raghuvanshi<\/a>
\nOren Barkan
\nSarangarajan Parthasarathy<\/a>
\nSebastian Braun<\/a>
\nShifeng Pan
\nShuayb Zarar<\/a>
\nSungjin Lee<\/a>
\nTasos Anastasakos
\nXiaoyang Chen
\nXuedong Huang<\/a>
\nYan Huang<\/a>
\nYao Tian
\nYashesh Gaur
\nYifan Gong
\nYong Zhao<\/p>\n

 Opens in a new tab<\/span><\/p>\n

A Pitch-Aware Approach to Single-Channel Speech Separation<\/strong>
\nTuesday, May 14, 2019 | 1:30 PM\u20133:30 PM | Music Source Separation and Spatial Audio | Poster Area E<\/p>\n

Ke Wang, Frank Soong<\/a>, Lei Xie<\/p>\n

A Sparsity Measure for Echo Density Growth in General Environments<\/strong>
\nTuesday, May 14, 2019 | 1:30 PM\u20133:30 PM | Acoustic Environments and Music Analysis | Poster Area D<\/p>\n

Helena Peic Tukuljac, Ville Pulkki, Hannes Gamper<\/a>, Keith Godin<\/strong>, Ivan Tashev<\/a>, Nikunj Raghuvanshi<\/a><\/p>\n

Blind Room Volume Estimation from Single-Channel Noisy Speech<\/strong>
\nTuesday, May 14, 2019 | 1:30 PM\u20133:30 PM | Acoustic Environments and Music Analysis | Poster Area D<\/p>\n

Andrea Genovese, Hannes Gamper<\/a>, Ville Pulkki, Nikunj Raghuvanshi<\/a>, Ivan Tashev<\/a><\/p>\n

Improving Binaural Ambisonics Decoding by Spherical Harmonics Domain Tapering and Coloration Compensation<\/strong>
\nTuesday, May 14, 2019 | 1:30 PM\u20133:30 PM | Music Source Separation and Spatial Audio | Poster Area E<\/p>\n

Christoph Hold, Hannes Gamper<\/a>, Ville Pulkki, Nikunj Raghuvanshi<\/a>, Ivan Tashev<\/a><\/p>\n

Static and Dynamic State Predictions for Acoustic Model Combination<\/strong>
\nTuesday, May 14, 2019 | 1:30 PM\u20133:30 PM | Deep Learning Applications I | Auditorium 2<\/p>\n

Kshitiz Kumar<\/strong>, Yifan Gong <\/strong><\/p>\n

\n

Gaussian Process LSTM Recurrent Neural Network Language Models for Speech Recognition<\/strong>
\nTuesday, May 14, 2019 | 5:30 PM\u20137:30 PM | Language Modeling, ASR and Punctuation Prediction | Poster Area C<\/p>\n

Max W.Y. Lam, Xie Chen<\/a>, Shoukang Hu, Jianwei Yu, Xunying Liu, Helen Meng<\/p>\n

Investigation of Sampling Techniques for Maximum Entropy Language Modeling Training<\/strong>
\nTuesday, May 14, 2019 | 5:30 PM\u20137:30 PM | Language Modeling, ASR and Punctuation Prediction | Poster Area C<\/p>\n

Xie Chen<\/a>, Jun Zhang<\/strong>, Tasos Anastasakos<\/strong>, Fil Alleva<\/p>\n

Recurrent Neural Network Language Model Training Using Natural Gradient<\/strong>
\nTuesday, May 14, 2019 | 5:30 PM\u20137:30 PM | Language Modeling, ASR and Punctuation Prediction | Poster Area C<\/p>\n

Jianwei Yu, Max W.Y. Lam, Xie Chen<\/a>, Shoukang Hu, Songxiang Liu, Xixin Wu, Xunying Liu, Helen Meng<\/p>\n

Towards Code-Switching ASR for End-to-End CTC Models<\/strong>
\nTuesday, May 14, 2019 | 5:30 PM\u20137:30 PM | Multi-lingual Speech Recognition | Poster Area A<\/p>\n

Ke Li, Jinyu Li<\/a>, Guoli Ye<\/strong>, Rui Zhao<\/strong>, Yifan Gong<\/strong><\/p>\n

\n

Adversarial Speaker Verification<\/strong>
\nWednesday, May 15, 2019 | 8:30 AM\u201310:30 AM | Features and Robustness for Speaker Identification | Poster Area B<\/p>\n

Zhong Meng<\/strong>, Yong Zhao<\/strong>, Jinyu Li<\/a>, Yifan Gong<\/strong><\/p>\n

Attention in Recurrent Neural Networks for Ransomware Detection<\/strong>
\nWednesday, May 15, 2019 | 8:30 AM\u201310:30 AM | Deep Learning III | Poster Area G<\/p>\n

Rakshit Agrawal, Jack W. Stokes<\/a>, Karthik Selvaraj<\/strong>, Mady Marinescu<\/strong><\/p>\n

Encrypted Speech Recognition Using Deep Polynomial Networks<\/strong>
\nWednesday, May 15, 2019 | 8:30 AM\u201310:30 AM | Novel Architectures and Training Strategies for ASR | Auditorium 1<\/p>\n

Shixiong Zhang, Yifan Gong<\/strong>, Dong Yu<\/p>\n

Single-Channel Speech Extraction Using Speaker Inventory and Attention Network<\/strong>
\nWednesday, May 15, 2019 | 8:30 AM\u201310:30 AM | Source Separation and Speech Enhancement I | Meeting Room 1<\/p>\n

Xiong Xiao<\/strong>, Zhuo Chen<\/strong>, Takuya Yoshioka<\/a>, Hakan Erdogan, Changliang Liu<\/strong>, Dimitrios Dimitriadis<\/a>, Jasha Droppo, Yifan Gong<\/strong><\/p>\n

Universal Acoustic Modeling Using Neural Mixture Models<\/strong>
\nWednesday, May 15, 2019 | 8:30 AM\u201310:30 AM | Novel Architectures and Training Strategies for ASR | Auditorium 1<\/p>\n

Amit Das<\/strong>, Jinyu Li<\/a>, Changliang Liu<\/strong>, Yifan Gong<\/strong><\/p>\n

\n

Adversarial Speaker Adaptation<\/strong>
\nWednesday, May 15, 2019 | 1:30 PM\u20133:30 PM | Feature Learning and Adaptation for ASR | Auditorium 1<\/p>\n

Zhong Meng<\/strong>, Jinyu Li<\/a>, Yifan Gong<\/strong><\/p>\n

Detecting Cyber Attacks Using Anomaly Detection with Explanations and Expert Feedback<\/strong>
\nWednesday, May 15, 2019 | 1:30 PM\u20133:30 PM | Learning Theory and Methods I | Auditorium 2<\/p>\n

Md Amran Siddiqui, Jack W. Stokes<\/a>, Christian Seifert<\/strong>, Evan Argyle<\/strong>, Robert McCann<\/strong>, Joshua Neil<\/strong>, Justin Carroll<\/strong><\/p>\n

\n

Directional Interference Suppression Using a Spatial Relative Transfer Function Feature<\/strong>
\nWednesday, May 15, 2019 | 4:00 PM\u20136:00 PM | Quality Measures and Sensor Array Processing | Poster Area D<\/p>\n

Sebastian Braun<\/a>, Ivan Tashev<\/a><\/p>\n

NN-Based Ordinal Regression for Assessing Fluency of ESL Speech<\/strong>
\nWednesday, May 15, 2019 | 4:00 PM\u20136:00 PM | Training Regimes for Emotion and Sentiment Analysis | Poster Area C<\/p>\n

Shaoguang Mao, Zhiyong Wu, Jingshuai Jiang<\/strong>, Peiyun Liu<\/strong>, Frank Soong<\/a><\/p>\n

Non-Intrusive Speech Quality Assessment Using Neural Networks<\/strong><\/a>
\nWednesday, May 15, 2019 | 4:00 PM\u20136:00 PM | Quality Measures and Sensor Array Processing | Poster Area D<\/p>\n

Anderson R. Avila, Hannes Gamper<\/a>, Chandan Reddy<\/strong>, Ross Cutler<\/strong>, Ivan Tashev<\/a>, Johannes Gehrke<\/a><\/p>\n

\n

Conditional Teacher-Student Learning<\/strong>
\nThursday, May 16, 2019 | 8:00 AM\u201310:00 AM | ASR Training Strategies and Toolkits | Poster Area A<\/p>\n

Zhong Meng<\/strong>, Jinyu Li<\/a>, Yong Zhao<\/strong>, Yifan Gong<\/strong><\/p>\n

Decoding Homomorphically Encrypted Flac Audio Without Decryption<\/strong>
\nThursday, May 16, 2019 | 8:00 AM\u201310:00 AM | Audio Security and Source Separation | Poster Area D<\/p>\n

Yuanyuan Tang, Bin Zhu<\/a>, Xiaojing Ma, Mathiopoulos P. Takis, Xia Xie, Hong Huang<\/p>\n

\n

Improving Layer Trajectory LSTM with Future Context Frames<\/strong>
\nThursday, May 16, 2019 | 1:00 PM\u20133:00 PM | New Features, Models and Representations\/Audio Visual ASR | Poster Area A<\/p>\n

Jinyu Li<\/a>, Liang Lu<\/strong>, Changliang Liu<\/strong>, Yifan Gong<\/strong><\/p>\n

\n

Contextual Out-of-Domain Utterance Handling with Counterfeit Data Augmentation<\/strong><\/a>
\nThursday, May 16, 2019 | 3:30 PM\u20135:30 PM | Dialogue | Syndicate 1<\/p>\n

Sungjin Lee<\/a>, Igor Shalyminov<\/p>\n

Dilated Residual Network with Multi-Head Self-Attention for Speech Emotion Recognition<\/strong>
\nThursday, May 16, 2019 | 3:30 PM\u20135:30 PM | Architectures for Emotion and Sentiment Analysis | Poster Area B<\/p>\n

Runnan Li, Zhiyong Wu, Jia Jia, Sheng Zhao<\/strong>, Helen Meng<\/p>\n

\n

Attentive Adversarial Learning for Domain-Invariant Training<\/strong>
\nThursday, May 16, 2019 | 6:00 PM\u20138:00 PM | Robust Speech Recognition | Poster Area A<\/p>\n

Zhong Meng<\/strong>, Jinyu Li<\/a>, Yifan Gong<\/strong><\/p>\n

Speech Super Resolution Generative Adversarial Network<\/strong>
\nThursday, May 16, 2019 | 6:00 PM\u20138:00 PM | Audio and Speech Applications | Poster Area G<\/p>\n

Sefik Emre Eskimez, Kazuhito Koishida<\/a><\/p>\n

Word Characters and Phone Pronunciation Embedding for ASR Confidence Classifier<\/strong>
\nThursday, May 16, 2019 | 6:00 PM\u20138:00 PM | Signal Processing for Emerging and Practical Applications | Poster Area E<\/p>\n

Session Chair: Ivan Tashev<\/a>
\nKshitiz Kumar<\/strong>, Tasos Anastasakos<\/strong>, Yifan Gong<\/strong><\/p>\n

\n

Acoustic and Lexical Sentiment Analysis for Customer Service Calls<\/strong><\/a>
\nFriday, May 17, 2019 | 8:30 AM\u201310:30 AM | Using Multiple Perspectives in Emotion and Sentiment Analysis | Syndicate 3<\/p>\n

Bryan Li, Dimitrios Dimitriadis<\/a>, Andreas Stolcke<\/a><\/p>\n

Domain Adversarial Training for Improving Keyword Spotting Performance of ESL Speech<\/strong>
\nFriday, May 17, 2019 | 8:30 AM\u201310:30 AM | Artificial Intelligence Based Human-Machine Conversation Technology for Interactive Education | Syndicate 1<\/p>\n

Session Chairs: Yao Qian, Helen Meng, Frank K. Soong<\/a>
\nJingyong Hou, Pengcheng Guo, Sining Sun, Frank K. Soong<\/a>, Wenping Hu<\/a>, Lei Xie<\/p>\n

Learning Latent Representations for Style Control and Transfer in End-to-End Speech Synthesis<\/strong>
\nFriday, May 17, 2019 | 8:30 AM\u201310:30 AM | Speech Synthesis II | Poster Area B<\/p>\n

Ya-Jie Zhang, Shifeng Pan<\/strong>, Lei He<\/strong>, Zhen-Hua Ling<\/p>\n

\n

Low-Latency Speaker-Independent Continuous Speech Separation<\/strong>
\nFriday, May 17, 2019 | 1:30 PM\u20133:30 PM | Speech Separation, Enhancement and Denoising | Poster Area A<\/p>\n

Takuya Yoshioka<\/a>, Zhuo Chen<\/strong>, Changliang Liu<\/strong>, Xiong Xiao<\/strong>, Hakan Erdogan, Dimitrios Dimitriadis<\/a><\/p>\n

\n

Cross Modal Audio Search and Retrieval with Joint Embeddings Based on Text and Audio<\/strong>
\nFriday, May 17, 2019 | 4:00 PM\u20136:00 PM | Multimedia Analysis | Poster Area C<\/p>\n

Benjamin Elizalde, Shuayb Zarar<\/a>, Bhiksha Raj<\/p>\n

Opens in a new tab<\/span><\/p>\n","tab-content":[{"id":0,"name":"About","content":"Microsoft is excited to be a Silver sponsor of the 44th<\/sup> International Conference on Acoustics, Speech, and Signal Processing (ICASSP)<\/a> May 12 \u2013 17, 2019, in Brighton, UK. Stop by our booth to chat with our experts, see demos of our latest research and find out more about career opportunities with Microsoft.\r\n

Session chairs<\/h3>\r\nFrank K. Soong<\/a>\r\nIvan Tashev<\/a>\r\nJinyu Li<\/a>\r\nDavid Wipf<\/a>\r\n

Microsoft attendees<\/h3>\r\nAmy Siebenthaler\r\nAndreas Stolcke<\/a>\r\nAnthony Stark\r\nDimitra Emmanouilidou<\/a>\r\nDimitrios Dimitriadis<\/a>\r\nEric Sun\r\nFei Zuo\r\nFrank K. Soong<\/a>\r\nHamid Palangi<\/a>\r\nHannes Gamper<\/a>\r\nIvan Tashev<\/a>\r\nJack Stokes\r\nJian Wu\r\nJianfeng Gao<\/a>\r\nJinyu Li<\/a>\r\nKazuhito Koishida<\/a>\r\nKshitiz Kumar\r\nLei He\r\nMichael Levit<\/a>\r\nMortaza Doulaty\r\nNanshan Zeng\r\nNikunj Raghuvanshi<\/a>\r\nOren Barkan\r\nSarangarajan Parthasarathy<\/a>\r\nSebastian Braun<\/a>\r\nShifeng Pan\r\nShuayb Zarar<\/a>\r\nSungjin Lee<\/a>\r\nTasos Anastasakos\r\nXiaoyang Chen\r\nXuedong Huang<\/a>\r\nYan Huang<\/a>\r\nYao Tian\r\nYashesh Gaur\r\nYifan Gong\r\nYong Zhao\r\n\r\n "},{"id":1,"name":"Accepted Papers","content":"A Pitch-Aware Approach to Single-Channel Speech Separation<\/strong>\r\nTuesday, May 14, 2019 | 1:30 PM\u20133:30 PM | Music Source Separation and Spatial Audio | Poster Area E\r\n

Ke Wang, Frank Soong<\/a>, Lei Xie<\/p>\r\nA Sparsity Measure for Echo Density Growth in General Environments<\/strong>\r\nTuesday, May 14, 2019 | 1:30 PM\u20133:30 PM | Acoustic Environments and Music Analysis | Poster Area D\r\n

Helena Peic Tukuljac, Ville Pulkki, Hannes Gamper<\/a>, Keith Godin<\/strong>, Ivan Tashev<\/a>, Nikunj Raghuvanshi<\/a><\/p>\r\nBlind Room Volume Estimation from Single-Channel Noisy Speech<\/strong>\r\nTuesday, May 14, 2019 | 1:30 PM\u20133:30 PM | Acoustic Environments and Music Analysis | Poster Area D\r\n

Andrea Genovese, Hannes Gamper<\/a>, Ville Pulkki, Nikunj Raghuvanshi<\/a>, Ivan Tashev<\/a><\/p>\r\nImproving Binaural Ambisonics Decoding by Spherical Harmonics Domain Tapering and Coloration Compensation<\/strong>\r\nTuesday, May 14, 2019 | 1:30 PM\u20133:30 PM | Music Source Separation and Spatial Audio | Poster Area E\r\n

Christoph Hold, Hannes Gamper<\/a>, Ville Pulkki, Nikunj Raghuvanshi<\/a>, Ivan Tashev<\/a><\/p>\r\nStatic and Dynamic State Predictions for Acoustic Model Combination<\/strong>\r\nTuesday, May 14, 2019 | 1:30 PM\u20133:30 PM | Deep Learning Applications I | Auditorium 2\r\n

Kshitiz Kumar<\/strong>, Yifan Gong <\/strong><\/p>\r\n\r\n\r\n

\r\n\r\nGaussian Process LSTM Recurrent Neural Network Language Models for Speech Recognition<\/strong>\r\nTuesday, May 14, 2019 | 5:30 PM\u20137:30 PM | Language Modeling, ASR and Punctuation Prediction | Poster Area C\r\n

Max W.Y. Lam, Xie Chen<\/a>, Shoukang Hu, Jianwei Yu, Xunying Liu, Helen Meng<\/p>\r\nInvestigation of Sampling Techniques for Maximum Entropy Language Modeling Training<\/strong>\r\nTuesday, May 14, 2019 | 5:30 PM\u20137:30 PM | Language Modeling, ASR and Punctuation Prediction | Poster Area C\r\n

Xie Chen<\/a>, Jun Zhang<\/strong>, Tasos Anastasakos<\/strong>, Fil Alleva<\/p>\r\nRecurrent Neural Network Language Model Training Using Natural Gradient<\/strong>\r\nTuesday, May 14, 2019 | 5:30 PM\u20137:30 PM | Language Modeling, ASR and Punctuation Prediction | Poster Area C\r\n

Jianwei Yu, Max W.Y. Lam, Xie Chen<\/a>, Shoukang Hu, Songxiang Liu, Xixin Wu, Xunying Liu, Helen Meng<\/p>\r\nTowards Code-Switching ASR for End-to-End CTC Models<\/strong>\r\nTuesday, May 14, 2019 | 5:30 PM\u20137:30 PM | Multi-lingual Speech Recognition | Poster Area A\r\n

Ke Li, Jinyu Li<\/a>, Guoli Ye<\/strong>, Rui Zhao<\/strong>, Yifan Gong<\/strong><\/p>\r\n\r\n\r\n

\r\n\r\nAdversarial Speaker Verification<\/strong>\r\nWednesday, May 15, 2019 | 8:30 AM\u201310:30 AM | Features and Robustness for Speaker Identification | Poster Area B\r\n

Zhong Meng<\/strong>, Yong Zhao<\/strong>, Jinyu Li<\/a>, Yifan Gong<\/strong><\/p>\r\nAttention in Recurrent Neural Networks for Ransomware Detection<\/strong>\r\nWednesday, May 15, 2019 | 8:30 AM\u201310:30 AM | Deep Learning III | Poster Area G\r\n

Rakshit Agrawal, Jack W. Stokes<\/a>, Karthik Selvaraj<\/strong>, Mady Marinescu<\/strong><\/p>\r\nEncrypted Speech Recognition Using Deep Polynomial Networks<\/strong>\r\nWednesday, May 15, 2019 | 8:30 AM\u201310:30 AM | Novel Architectures and Training Strategies for ASR | Auditorium 1\r\n

Shixiong Zhang, Yifan Gong<\/strong>, Dong Yu<\/p>\r\nSingle-Channel Speech Extraction Using Speaker Inventory and Attention Network<\/strong>\r\nWednesday, May 15, 2019 | 8:30 AM\u201310:30 AM | Source Separation and Speech Enhancement I | Meeting Room 1\r\n

Xiong Xiao<\/strong>, Zhuo Chen<\/strong>, Takuya Yoshioka<\/a>, Hakan Erdogan, Changliang Liu<\/strong>, Dimitrios Dimitriadis<\/a>, Jasha Droppo, Yifan Gong<\/strong><\/p>\r\nUniversal Acoustic Modeling Using Neural Mixture Models<\/strong>\r\nWednesday, May 15, 2019 | 8:30 AM\u201310:30 AM | Novel Architectures and Training Strategies for ASR | Auditorium 1\r\n

Amit Das<\/strong>, Jinyu Li<\/a>, Changliang Liu<\/strong>, Yifan Gong<\/strong><\/p>\r\n\r\n\r\n

\r\n\r\nAdversarial Speaker Adaptation<\/strong>\r\nWednesday, May 15, 2019 | 1:30 PM\u20133:30 PM | Feature Learning and Adaptation for ASR | Auditorium 1\r\n

Zhong Meng<\/strong>, Jinyu Li<\/a>, Yifan Gong<\/strong><\/p>\r\nDetecting Cyber Attacks Using Anomaly Detection with Explanations and Expert Feedback<\/strong>\r\nWednesday, May 15, 2019 | 1:30 PM\u20133:30 PM | Learning Theory and Methods I | Auditorium 2\r\n

Md Amran Siddiqui, Jack W. Stokes<\/a>, Christian Seifert<\/strong>, Evan Argyle<\/strong>, Robert McCann<\/strong>, Joshua Neil<\/strong>, Justin Carroll<\/strong><\/p>\r\n\r\n\r\n

\r\n\r\nDirectional Interference Suppression Using a Spatial Relative Transfer Function Feature<\/strong>\r\nWednesday, May 15, 2019 | 4:00 PM\u20136:00 PM | Quality Measures and Sensor Array Processing | Poster Area D\r\n

Sebastian Braun<\/a>, Ivan Tashev<\/a><\/p>\r\nNN-Based Ordinal Regression for Assessing Fluency of ESL Speech<\/strong>\r\nWednesday, May 15, 2019 | 4:00 PM\u20136:00 PM | Training Regimes for Emotion and Sentiment Analysis | Poster Area C\r\n

Shaoguang Mao, Zhiyong Wu, Jingshuai Jiang<\/strong>, Peiyun Liu<\/strong>, Frank Soong<\/a><\/p>\r\nNon-Intrusive Speech Quality Assessment Using Neural Networks<\/strong><\/a>\r\nWednesday, May 15, 2019 | 4:00 PM\u20136:00 PM | Quality Measures and Sensor Array Processing | Poster Area D\r\n

Anderson R. Avila, Hannes Gamper<\/a>, Chandan Reddy<\/strong>, Ross Cutler<\/strong>, Ivan Tashev<\/a>, Johannes Gehrke<\/a><\/p>\r\n\r\n\r\n

\r\n\r\nConditional Teacher-Student Learning<\/strong>\r\nThursday, May 16, 2019 | 8:00 AM\u201310:00 AM | ASR Training Strategies and Toolkits | Poster Area A\r\n

Zhong Meng<\/strong>, Jinyu Li<\/a>, Yong Zhao<\/strong>, Yifan Gong<\/strong><\/p>\r\nDecoding Homomorphically Encrypted Flac Audio Without Decryption<\/strong>\r\nThursday, May 16, 2019 | 8:00 AM\u201310:00 AM | Audio Security and Source Separation | Poster Area D\r\n

Yuanyuan Tang, Bin Zhu<\/a>, Xiaojing Ma, Mathiopoulos P. Takis, Xia Xie, Hong Huang<\/p>\r\n\r\n\r\n

\r\n\r\nImproving Layer Trajectory LSTM with Future Context Frames<\/strong>\r\nThursday, May 16, 2019 | 1:00 PM\u20133:00 PM | New Features, Models and Representations\/Audio Visual ASR | Poster Area A\r\n

Jinyu Li<\/a>, Liang Lu<\/strong>, Changliang Liu<\/strong>, Yifan Gong<\/strong><\/p>\r\n\r\n\r\n

\r\n\r\nContextual Out-of-Domain Utterance Handling with Counterfeit Data Augmentation<\/strong><\/a>\r\nThursday, May 16, 2019 | 3:30 PM\u20135:30 PM | Dialogue | Syndicate 1\r\n

Sungjin Lee<\/a>, Igor Shalyminov<\/p>\r\nDilated Residual Network with Multi-Head Self-Attention for Speech Emotion Recognition<\/strong>\r\nThursday, May 16, 2019 | 3:30 PM\u20135:30 PM | Architectures for Emotion and Sentiment Analysis | Poster Area B\r\n

Runnan Li, Zhiyong Wu, Jia Jia, Sheng Zhao<\/strong>, Helen Meng<\/p>\r\n\r\n\r\n

\r\n\r\nAttentive Adversarial Learning for Domain-Invariant Training<\/strong>\r\nThursday, May 16, 2019 | 6:00 PM\u20138:00 PM | Robust Speech Recognition | Poster Area A\r\n

Zhong Meng<\/strong>, Jinyu Li<\/a>, Yifan Gong<\/strong><\/p>\r\nSpeech Super Resolution Generative Adversarial Network<\/strong>\r\nThursday, May 16, 2019 | 6:00 PM\u20138:00 PM | Audio and Speech Applications | Poster Area G\r\n

Sefik Emre Eskimez, Kazuhito Koishida<\/a><\/p>\r\nWord Characters and Phone Pronunciation Embedding for ASR Confidence Classifier<\/strong>\r\nThursday, May 16, 2019 | 6:00 PM\u20138:00 PM | Signal Processing for Emerging and Practical Applications | Poster Area E\r\n

Session Chair: Ivan Tashev<\/a>\r\nKshitiz Kumar<\/strong>, Tasos Anastasakos<\/strong>, Yifan Gong<\/strong><\/p>\r\n\r\n\r\n

\r\n\r\nAcoustic and Lexical Sentiment Analysis for Customer Service Calls<\/strong><\/a>\r\nFriday, May 17, 2019 | 8:30 AM\u201310:30 AM | Using Multiple Perspectives in Emotion and Sentiment Analysis | Syndicate 3\r\n

Bryan Li, Dimitrios Dimitriadis<\/a>, Andreas Stolcke<\/a><\/p>\r\nDomain Adversarial Training for Improving Keyword Spotting Performance of ESL Speech<\/strong>\r\nFriday, May 17, 2019 | 8:30 AM\u201310:30 AM | Artificial Intelligence Based Human-Machine Conversation Technology for Interactive Education | Syndicate 1\r\n

Session Chairs: Yao Qian, Helen Meng, Frank K. Soong<\/a>\r\nJingyong Hou, Pengcheng Guo, Sining Sun, Frank K. Soong<\/a>, Wenping Hu<\/a>, Lei Xie<\/p>\r\nLearning Latent Representations for Style Control and Transfer in End-to-End Speech Synthesis<\/strong>\r\nFriday, May 17, 2019 | 8:30 AM\u201310:30 AM | Speech Synthesis II | Poster Area B\r\n

Ya-Jie Zhang, Shifeng Pan<\/strong>, Lei He<\/strong>, Zhen-Hua Ling<\/p>\r\n\r\n\r\n

\r\n\r\nLow-Latency Speaker-Independent Continuous Speech Separation<\/strong>\r\nFriday, May 17, 2019 | 1:30 PM\u20133:30 PM | Speech Separation, Enhancement and Denoising | Poster Area A\r\n

Takuya Yoshioka<\/a>, Zhuo Chen<\/strong>, Changliang Liu<\/strong>, Xiong Xiao<\/strong>, Hakan Erdogan, Dimitrios Dimitriadis<\/a><\/p>\r\n\r\n\r\n

\r\n\r\nCross Modal Audio Search and Retrieval with Joint Embeddings Based on Text and Audio<\/strong>\r\nFriday, May 17, 2019 | 4:00 PM\u20136:00 PM | Multimedia Analysis | Poster Area C\r\n

Benjamin Elizalde, Shuayb Zarar<\/a>, Bhiksha Raj<\/p>"}],"msr_startdate":"2019-05-12","msr_enddate":"2019-05-17","msr_event_time":"","msr_location":"Brighton, United Kingdom","msr_event_link":"","msr_event_recording_link":"","msr_startdate_formatted":"May 12, 2019","msr_register_text":"Watch now","msr_cta_link":"","msr_cta_text":"","msr_cta_bi_name":"","featured_image_thumbnail":"\"Photo","event_excerpt":"Microsoft is excited to be a Silver sponsor of the 44th International Conference on Acoustics, Speech, and Signal Processing (ICASSP) May 12 \u2013 17, 2019, in Brighton, UK.","msr_research_lab":[199560,199565],"related-researchers":[],"msr_impact_theme":[],"related-academic-programs":[],"related-groups":[],"related-projects":[],"related-opportunities":[],"related-publications":[574680,595390,595402],"related-videos":[],"related-posts":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event\/578437","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-event"}],"version-history":[{"count":5,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event\/578437\/revisions"}],"predecessor-version":[{"id":1147046,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event\/578437\/revisions\/1147046"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/581446"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=578437"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=578437"},{"taxonomy":"msr-region","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-region?post=578437"},{"taxonomy":"msr-event-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event-type?post=578437"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=578437"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=578437"},{"taxonomy":"msr-program-audience","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-program-audience?post=578437"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=578437"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=578437"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}