{"id":474855,"date":"2018-03-22T07:48:55","date_gmt":"2018-03-22T14:48:55","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-event&p=474855"},"modified":"2018-07-03T06:47:44","modified_gmt":"2018-07-03T13:47:44","slug":"icassp-2018","status":"publish","type":"msr-event","link":"https:\/\/www.microsoft.com\/en-us\/research\/event\/icassp-2018\/","title":{"rendered":"Microsoft Research @ ICASSP 2018"},"content":{"rendered":"

Venue:<\/strong> Calgary Telus Convention Center (opens in new tab)<\/span><\/a>
\n120 Ninth Avenue SE
\nCalgary, Alberta
\nCanada T2G 0P3<\/p>\n

Website:<\/strong> ICASSP 2018 (opens in new tab)<\/span><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

Venue: Calgary Telus Convention Center 120 Ninth Avenue SE Calgary, Alberta Canada T2G 0P3 Website: ICASSP 2018<\/p>\n","protected":false},"featured_media":475878,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"msr_startdate":"2018-04-15","msr_enddate":"2018-04-20","msr_location":"Calgary, Alberta","msr_expirationdate":"","msr_event_recording_link":"","msr_event_link":"https:\/\/2018.ieeeicassp.org\/","msr_event_link_redirect":false,"msr_event_time":"","msr_hide_region":false,"msr_private_event":false,"footnotes":""},"research-area":[13556],"msr-region":[197900],"msr-event-type":[197941],"msr-video-type":[],"msr-locale":[268875],"msr-program-audience":[],"msr-post-option":[],"msr-impact-theme":[],"class_list":["post-474855","msr-event","type-msr-event","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-region-north-america","msr-event-type-conferences","msr-locale-en_us"],"msr_about":"Venue:<\/strong> Calgary Telus Convention Center<\/a>\r\n120 Ninth Avenue SE\r\nCalgary, Alberta\r\nCanada T2G 0P3\r\n\r\nWebsite:<\/strong> ICASSP 2018<\/a>","tab-content":[{"id":0,"name":"About","content":"Microsoft is proud to be a Silver sponsor of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing<\/a> April 15-20, 2018 at the Calgary Telus Convention Center in Calgary, Alberta.\r\n\r\nICASSP is the world\u2019s largest and most comprehensive technical conference focused on signal processing and its applications. The conference introduces new developments in the field and provides an engaging forum to exchange ideas with researchers and developers.\r\n\r\nMicrosoft has 29 accepted papers at ICASSP and several researchers in attendance. We encourage you to stop by our booth (D1) to talk to our researchers and learn more about opportunities available with Microsoft.\r\n

Microsoft Attendees<\/h2>\r\nAnthony Stark\r\nChaojun Liu\r\nDimitrios Dimitriadis\r\nFil Alleva<\/a>\r\nGeorge Polovets\r\nHakan Erdogan<\/a>\r\nJasha Droppo<\/a>\r\nJinyu Li<\/a>\r\nLi Jiang\r\nNick Kibre\r\nPartha Parthasarathy\r\nRui Zhao\r\nTakuya Yoshioka<\/a>\r\nXuedong Huang<\/a>\r\nYifan Gong\r\nYong Zhao\r\n

Tutorials<\/h2>\r\n

Replacing\/Enhancing Iterative Algorithms with Deep Neural Networks\r\nMonday, April 16, 2018\u00a0| 1:30 PM-5:00 PM<\/h4>\r\n

David Wipf<\/strong><\/a><\/p>"},{"id":1,"name":"Accepted Papers","content":"

Developing Far-Field Speaker System Via Teacher-Student Learning<\/a><\/h4>\r\n

Jinyu Li<\/strong><\/a>, Rui Zhao, Zhuo Chen, Changliang Liu, Xiong Xiao, Guoli Ye, Yifan Gong<\/p>\r\n\r\n

Advancing Connectionist Temporal Classification with Attention Modeling<\/a><\/h4>\r\n

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

Multi-Microphone Neural Speech Separation for Far-Field Multi-Talker Speech Recognition<\/a><\/h4>\r\n

Takuya Yoshioka<\/strong><\/a>, Hakan Erdogan<\/strong><\/a>, Zhuo Chen, Fil Alleva<\/strong><\/a><\/p>\r\n\r\n

Sequence Modeling in Unsupervised Single-Channel Overlapped Speech Recognition<\/a><\/h4>\r\n

Zhehuai Chen, Jasha Droppo<\/strong><\/a><\/p>\r\n\r\n

Single Channel Speech Separation with Constrained Utterance Level Permutation Invariant Training Using GRID LSTM<\/h4>\r\n

Chenglin Xu, Wei Rao, Xiong Xiao, Eng Siong Chng, Haizhou Li<\/p>\r\n\r\n

A Study of All-Convolutional Encoders for\u00a0 Connectionist Temporal Classification<\/h4>\r\n

Kalpesh Krishna, Liang Lu, Kevin Gimpel, Karen Livescu<\/p>\r\n\r\n

Adversarial Teacher-Student Learning for Unsupervised Domain Adaptation<\/a><\/h4>\r\n

Zhong Meng, Jinyu Li<\/strong><\/a>, Yifan Gong, Biing-Hwang (Fred) Juang<\/p>\r\n\r\n

Speaker-Invariant Training via Adversarial Learning<\/a><\/h4>\r\n

Zhong Meng, Jinyu Li<\/strong><\/a>, Zhuo Chen, Yong Zhao, Vadim Mazalov, Yifan Gong, Biing-Hwang (Fred) Juang<\/p>\r\n\r\n

Exploring Practical Aspects of Neural Mask-Based Beamforming for Far-Field Speech Recognition<\/a><\/h4>\r\n

Christoph Boeddeker, Hakan Erdogan<\/strong><\/a>, Takuya Yoshioka<\/strong><\/a>, Reinhold Haeb-Umbach<\/p>\r\n\r\n

Efficient Integration of Fixed Beamformers and Speach Separation Networks for Multi-Channel Far-Field Speech Separation<\/a><\/h4>\r\n

Zhuo Chen, Takuya Yoshioka<\/strong><\/a>, Xiong Xiao, Jinyu Li<\/strong><\/a>, Mike Seltzer, Yifan Gong<\/p>\r\n\r\n

Improving End-of-Turn Detection in Spoken Dialogues by Detecting Speaker Intentions as a Secondary Task<\/a><\/h4>\r\n

Zakaria Aldeneh, Dimitrios Dimitriadis, Emily Mower Provost<\/p>\r\n\r\n

Exploring sequential characteristics in speaker bottleneck feature for text-dependent speaker verification<\/h4>\r\n

Liping Chen, Yong Zhao, Shi-Xiong Zhang, Jie Li, Guoli Ye, Frank Soong<\/strong><\/a><\/p>\r\n\r\n

Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning<\/a><\/h4>\r\n

Baolin Peng, Xiujun Li<\/strong><\/a>, Jianfeng Gao<\/strong><\/a>, Jingjing Liu<\/strong><\/a>, Yun-Nung Chen, Kam-Fai Wong<\/p>\r\n\r\n

Limiting Numerical Precision of Neural Networks to Achieve Real-Time Voice Activity Detection<\/a><\/h4>\r\n

Jong Hwan Ko, Josh Fromm, Matthai Philipose<\/strong><\/a>, Ivan Tashev<\/strong><\/a>, Shuayb Zarar<\/strong><\/a><\/p>\r\n\r\n

Towards Language-Universal End-to-End Speech Recognition<\/h4>\r\n

Suyoun Kim, Michael Seltzer<\/p>\r\n\r\n

Advancing Acoustic-to-Word CTC Model<\/a><\/h4>\r\n

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

Constrained Convolutional-Recurrent Networks to Improve Speech Quality with Low Impact on Recognition Accuracy<\/a><\/h4>\r\n

Rasool Fakoor, Xiaodong He, Ivan Tashev<\/strong><\/a>, Shuayb Zarar<\/strong><\/a><\/p>\r\n\r\n

A Hybrid Approach to Combining Conventional and Deep Learning Techniques for Single-Channel Speech Enhancement and Recognition<\/a><\/h4>\r\n

Yanhui Tu, Ivan Tashev<\/strong><\/a>, Shuayb Zarar<\/strong><\/a>, Chin-Hui Lee<\/p>\r\n\r\n

Deep Learning Based Speech Beamforming<\/h4>\r\n

Kaizhi Qian, Yang Zhang, Shiyu Chang, Xuesong Yang, Dinei Florencio<\/strong><\/a>, Mark Hasegawa-Johnson<\/p>\r\n\r\n

Convolutional-Recurrent Neural Networks for Speech Enhancement<\/a><\/h4>\r\n

Han Zhao, Shuayb Zarar<\/strong><\/a>, Ivan Tashev<\/strong><\/a>, Chin-Hui Lee<\/p>\r\n\r\n

Neural Sequential Malware Detection with Parameters<\/h4>\r\n

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

Spatial Audio Feature Discovery with Convolutional Neural Networks<\/a><\/h4>\r\n

Etienne Thuillier, Hannes Gamper<\/strong><\/a>, Ivan Tashev<\/strong><\/a><\/p>\r\n\r\n

The Microsoft 2017 Conversational Speech Recognition System<\/a><\/h4>\r\n

Wayne Xiong<\/strong><\/a>, Lingfeng Wu, Fil Alleva<\/strong><\/a>, Jasha Droppo<\/strong><\/a>, Xuedong Huang<\/strong><\/a>, Andreas Stolcke<\/strong><\/a><\/p>\r\n\r\n

Domain and Speaker Adaptation for Cortana Speech Recognition<\/a><\/h4>\r\n

Yong Zhao, Jinyu Li<\/strong><\/a>, Shixiong Zhang, Liping Chen, Yifan Gong<\/p>\r\n\r\n

Augmented Data and Improved Noise Residual-Based CNN for Printer Source Identification<\/h4>\r\n

Sharad Joshi, Mohit Lamba, Vivek Goyal, Nitin Khanna<\/p>\r\n\r\n

Robust Detection of Epileptic Seizures Using Deep Neural Networks<\/h4>\r\n

Ramy Hussein, Hamid Palangi<\/strong><\/a>, Z. Jane Wang, Rabab Ward<\/p>"}],"msr_startdate":"2018-04-15","msr_enddate":"2018-04-20","msr_event_time":"","msr_location":"Calgary, Alberta","msr_event_link":"https:\/\/2018.ieeeicassp.org\/","msr_event_recording_link":"","msr_startdate_formatted":"April 15, 2018","msr_register_text":"Watch now","msr_cta_link":"https:\/\/2018.ieeeicassp.org\/","msr_cta_text":"Watch now","msr_cta_bi_name":"Event Register","featured_image_thumbnail":"\"\"","event_excerpt":"Microsoft is proud to be a Silver sponsor of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing April 15-20, 2018 at the Calgary Telus Convention Center in Calgary, Alberta. ICASSP is the world\u2019s largest and most comprehensive technical conference focused on signal processing and its applications. The conference introduces new developments in the field and provides an engaging forum to exchange ideas with researchers and developers. Microsoft has 29 accepted papers at…","msr_research_lab":[],"related-researchers":[],"msr_impact_theme":[],"related-academic-programs":[],"related-groups":[],"related-projects":[],"related-opportunities":[],"related-publications":[574356],"related-videos":[],"related-posts":[485208],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event\/474855"}],"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\/474855\/revisions"}],"predecessor-version":[{"id":474876,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event\/474855\/revisions\/474876"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/475878"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=474855"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=474855"},{"taxonomy":"msr-region","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-region?post=474855"},{"taxonomy":"msr-event-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event-type?post=474855"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=474855"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=474855"},{"taxonomy":"msr-program-audience","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-program-audience?post=474855"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=474855"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=474855"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}