| 2025 | ICASSP | Directional Source Separation for Robust Speech Recognition on Smart Glasses. | Tiantian Feng, Ju Lin, Yiteng Huang, Weipeng He, Kaustubh Kalgaonkar, Niko Moritz, Li Wan, Xin Lei, Ming Sun, Frank Seide |
| 2025 | ICASSP | Efficient Streaming LLM for Speech Recognition. | Junteng Jia, Gil Keren, Wei Zhou, Egor Lakomkin, Xiaohui Zhang, Chunyang Wu, Frank Seide, Jay Mahadeokar, Ozlem Kalinli |
| 2025 | ICASSP | Transcribing and Translating, Fast and Slow: Joint Speech Translation and Recognition. | Niko Moritz, Ruiming Xie, Yashesh Gaur, Ke Li, Simone Merello, Zeeshan Ahmed, Frank Seide, Christian Fuegen |
| 2025 | Interspeech | Directional Speech Recognition with Full-Duplex Capability. | Ju Lin, Yiteng Huang, Ming Sun, Frank Seide, Florian Metze |
| 2024 | ICASSP | Effective Internal Language Model Training and Fusion for Factorized Transducer Model. | Jinxi Guo, Niko Moritz, Yingyi Ma, Frank Seide, Chunyang Wu, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer |
| 2024 | ICASSP | AGADIR: Towards Array-Geometry Agnostic Directional Speech Recognition. | Ju Lin, Niko Moritz, Yiteng Huang, Ruiming Xie, Ming Sun, Christian Fuegen, Frank Seide |
| 2024 | Interspeech | Navigating the Minefield of MT Beam Search in Cascaded Streaming Speech Translation. | Rastislav Rabatin, Frank Seide, Ernie Chang |
| 2024 | Interspeech | Speech ReaLLM - Real-time Speech Recognition with Multimodal Language Models by Teaching the Flow of Time. | Frank Seide, Yangyang Shi, Morrie Doulaty, Yashesh Gaur, Junteng Jia, Chunyang Wu |
| 2023 | ASRU | Joint Federated Learning and Personalization for on-Device ASR. | Junteng Jia, Ke Li, Mani Malek, Kshitiz Malik, Jay Mahadeokar, Ozlem Kalinli, Frank Seide |
| 2023 | ICASSP | Factorized Blank Thresholding for Improved Runtime Efficiency of Neural Transducers. | Duc Le, Frank Seide, Yuhao Wang, Yang Li, Kjell Schubert, Ozlem Kalinli, Michael L. Seltzer |
| 2023 | Interspeech | Directional Speech Recognition for Speaker Disambiguation and Cross-talk Suppression. | Ju Lin, Niko Moritz, Ruiming Xie, Kaustubh Kalgaonkar, Christian Fuegen, Frank Seide |
| 2022 | Interspeech | Federated Domain Adaptation for ASR with Full Self-Supervision. | Junteng Jia, Jay Mahadeokar, Weiyi Zheng, Yuan Shangguan, Ozlem Kalinli, Frank Seide |
| 2018 | ACL | Marian: Fast Neural Machine Translation in C++. | Marcin Junczys-Dowmunt, Roman Grundkiewicz, Tomasz Dwojak, Hieu Hoang, Kenneth Heafield, Tom Neckermann, Frank Seide, Ulrich Germann, Alham Fikri Aji, Nikolay Bogoychev, Andr F. T. Martins, Alexandra Birch |
| 2017 | ICASSP | The microsoft 2016 conversational speech recognition system. | Wayne Xiong, Jasha Droppo, Xuedong Huang, Frank Seide, Mike Seltzer, Andreas Stolcke, Dong Yu, Geoffrey Zweig |
| 2016 | KDD | CNTK: Microsoft's Open-Source Deep-Learning Toolkit. | Frank Seide, Amit Agarwal |
| 2015 | ASRU | Deep bi-directional recurrent networks over spectral windows. | Abdel-rahman Mohamed, Frank Seide, Dong Yu, Jasha Droppo, Andreas Stolcke, Geoffrey Zweig, Gerald Penn |
| 2014 | ICASSP | On parallelizability of stochastic gradient descent for speech DNNS. | Frank Seide, Hao Fu, Jasha Droppo, Gang Li, Dong Yu |
| 2014 | Interspeech | 1-bit stochastic gradient descent and its application to data-parallel distributed training of speech DNNs. | Frank Seide, Hao Fu, Jasha Droppo, Gang Li, Dong Yu |
| 2014 | Interspeech | An introduction to computational networks and the computational network toolkit (invited talk). | Dong Yu, Adam Eversole, Michael L. Seltzer, Kaisheng Yao, Brian Guenter, Oleksii Kuchaiev, Frank Seide, Huaming Wang, Jasha Droppo, Zhiheng Huang, Geoffrey Zweig, Christopher J. Rossbach, Jon Currey |
| 2013 | ICASSP | Recent advances in deep learning for speech research at Microsoft. | Li Deng, Jinyu Li, Jui-Ting Huang, Kaisheng Yao, Dong Yu, Frank Seide, Michael L. Seltzer, Geoffrey Zweig, Xiaodong He, Jason D. Williams, Yifan Gong, Alex Acero |
| 2013 | ICASSP | Error back propagation for sequence training of Context-Dependent Deep NetworkS for conversational speech transcription. | Hang Su, Gang Li, Dong Yu, Frank Seide |
| 2013 | ICASSP | KL-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition. | Dong Yu, Kaisheng Yao, Hang Su, Gang Li, Frank Seide |
| 2013 | Interspeech | A new language independent, photo-realistic talking head driven by voice only. | Xinjian Zhang, Lijuan Wang, Gang Li, Frank Seide, Frank K. Soong |
| 2012 | ICASSP | Exploiting sparseness in deep neural networks for large vocabulary speech recognition. | Dong Yu, Frank Seide, Gang Li, Li Deng |
| 2012 | ICML | Conversational Speech Transcription Using Context-Dependent Deep Neural Networks. | Dong Yu, Frank Seide, Gang Li |
| 2012 | Interspeech | Pipelined Back-Propagation for Context-Dependent Deep Neural Networks. | Xie Chen, Adam Eversole, Gang Li, Dong Yu, Frank Seide |
| 2012 | Interspeech | ClippyScript: A Programming Language for Multi-Domain Dialogue Systems. | Frank Seide, Sean McDirmid |
| 2012 | Interspeech | Voice Activity Detection Using Speech Recognizer Feedback. | Kit Thambiratnam, Weiwu Zhu, Frank Seide |
| 2012 | Interspeech | Large Vocabulary Speech Recognition Using Deep Tensor Neural Networks. | Dong Yu, Li Deng, Frank Seide |
| 2011 | ASRU | Subword-based multi-span pronunciation adaptation for recognizing accented speech. | Timo Mertens, Kit Thambiratnam, Frank Seide |
| 2011 | ASRU | Feature engineering in Context-Dependent Deep Neural Networks for conversational speech transcription. | Frank Seide, Gang Li, Xie Chen, Dong Yu |
| 2011 | ICASSP | Leveraging the Web for automatically generating indexable and browsable keywords for speech files. | Kishan Thambiratnam, Gang Li, Sha Meng, Frank Seide |
| 2011 | Interspeech | Conversational Speech Transcription Using Context-Dependent Deep Neural Networks. | Frank Seide, Gang Li, Dong Yu |
| 2010 | ICASSP | Music rhythm characterization with application to workout-mix generation. | Qian Lin, Lie Lu, Christopher Weare, Frank Seide |
| 2010 | ICASSP | Vocabulary and language model adaptation using just one speech file. | Sha Meng, Kishan Thambiratnam, Yimeng Lin, Lifang Wang, Gang Li, Frank Seide |
| 2010 | Interspeech | On using missing-feature theory with cepstral features - approximations to the multivariate integral. | Frank Seide, Pei Zhao |
| 2009 | ASRU | Automatic punctuation generation for speech. | Wenzhu Shen, Roger Peng Yu, Frank Seide, Ji Wu |
| 2009 | ICASSP | Unsupervised speaker adaptation for telephone call transcription. | R. Wallace, Kishan Thambiratnam, Frank Seide |
| 2009 | ICASSP | Learning a music similarity measure on automatic annotations with application to playlist generation. | Linxing Xiao, Lie Lu, Frank Seide, Jie Zhou |
| 2009 | Interspeech | Unsupervised lattice-based acoustic model adaptation for speaker-dependent conversational telephone speech transcription. | Kishan Thambiratnam, Frank Seide |
| 2008 | ICASSP | Mobile ringtone search through query by humming. | Lie Lu, Frank Seide |
| 2008 | ICASSP | Fusing multiple systems into a compact lattice index for chinese spoken term detection. | Sha Meng, Peng Yu, Jia Liu, Frank Seide |
| 2008 | ICASSP | Approximateword-lattice indexing with text indexers: Time-Anchored Lattice Expansion. | Peng Yu, Yu Shi, Frank Seide |
| 2008 | Interspeech | Addressing the out-of-vocabulary problem for large-scale Chinese spoken term detection. | Sha Meng, Jian Shao, Roger Peng Yu, Jia Liu, Frank Seide |
| 2008 | Interspeech | Towards vocabulary-independent speech indexing for large-scale repositories. | Jian Shao, Roger Peng Yu, Qingwei Zhao, Yonghong Yan, Frank Seide |
| 2008 | Interspeech | GPU-accelerated Gaussian clustering for fMPE discriminative training. | Yu Shi, Frank Seide, Frank K. Soong |
| 2008 | Interspeech | Fragmented context-dependent syllable acoustic models. | Kishan Thambiratnam, Frank Seide |
| 2007 | ASRU | A study of lattice-based spoken term detection for Chinese spontaneous speech. | Sha Meng, Peng Yu, Frank Seide, Jia Liu |
| 2007 | ASRU | Towards spoken-document retrieval for the enterprise: Approximate word-lattice indexing with text indexers. | Frank Seide, Peng Yu, Yu Shi |
| 2007 | ICASSP | A Hidden-State Maximum Entropy Model Forword Confidence Estimation. | Peng Yu, Jie Xu, Guo-Liang Zhang, Yuchou Chang, Frank Seide |
| 2007 | Interspeech | Online vocabulary adaptation using limited adaptation data. | C. E. Liu, Kishan Thambiratnam, Frank Seide |
| 2007 | Interspeech | Learning spoken document similarity and recommendation using supervised probabilistic latent semantic analysis. | Kishan Thambiratnam, Frank Seide |
| 2006 | ICASSP | Maximum Entropy Based Normalization Of Word Posteriors For Phonetic And Lvcsr Lattice Search. | Peng Yu, Duo Zhang, Frank Seide |
| 2006 | NAACL | Towards Spoken-Document Retrieval for the Internet: Lattice Indexing For Large-Scale Web-Search Architectures. | Zheng-Yu Zhou, Peng Yu, Ciprian Chelba, Frank Seide |
| 2005 | ICASSP | Fast Two-Stage Vocabulary-Independent Search In Spontaneous Speech. | Peng Yu, Frank Seide |
| 2005 | NAACL | Searching the Audio Notebook: Keyword Search in Recorded Conversation. | Peng Yu, Kaijiang Chen, Lie Lu, Frank Seide |
| 2004 | ICASSP | Vocabulary-independent search in spontaneous speech. | Frank Seide, Peng Yu, Chengyuan Ma, Eric Chang |
| 2003 | ICASSP | Coarticulation modeling by embedding a target-directed hidden trajectory model into HMM - MAP decoding and evaluation. | Frank Seide, Jian-Lai Zhou, Li Deng |
| 2003 | ICASSP | Coarticulation modeling by embedding a target-directed hidden trajectory model into HMM - model and training. | Jian-Lai Zhou, Frank Seide, Li Deng |
| 2003 | Interspeech | An improved model-based speaker segmentation system. | Peng Yu, Frank Seide, Chengyuan Ma, Eric Chang |
| 2001 | ICASSP | Rapid speaker adaptation using a priori knowledge by eigenspace analysis of MLLR parameters. | Nick J.-C. Wang, Sammy S.-M. Lee, Frank Seide, Lin-Shan Lee |
| 2000 | ICASSP | Pitch tracking and tone features for Mandarin speech recognition. | Hank Chang-Han Huang, Frank Seide |
| 2000 | Interspeech | Improvements of the Philips 2000 Taiwan Mandarin benchmark system. | Yuan-Fu Liao, Nick J.-C. Wang, Max Huang, Hank Huang, Frank Seide |
| 2000 | Interspeech | Two-stream modeling of Mandarin tones. | Frank Seide, Nick J.-C. Wang |
| 2000 | Interspeech | MAT-2000 - design, collection, and validation of a Mandarin 2000-speaker telephone speech database. | Hsiao-Chuan Wang, Frank Seide, Chiu-yu Tseng, Lin-Shan Lee |
| 1999 | Interspeech | Development of the philips 1999 taiwan Mandarin benchmark system. | Chiwei Che, Nick J.-C. Wang, Max Huang, Hank Huang, Frank Seide |
| 1997 | Interspeech | Towards an automated directory information system. | Frank Seide, Andreas Kellner |
| 1996 | Interspeech | A comparison of time conditioned and word conditioned search techniques for large vocabulary speech recognition. | Stefan Ortmanns, Hermann Ney, Frank Seide, Ingo Lindam |
| 1996 | Interspeech | Improving speech understanding by incorporating database constraints and dialogue history. | Frank Seide, Bernhard Rueber, Andreas Kellner |
| 1996 | Interspeech | A word graph based n-best search in continuous speech recognition. | Bach-Hiep Tran, Frank Seide, Volker Steinbiss |
| 1995 | Interspeech | Fast likelihood computation for continuous-mixture densities using a tree-based nearest neighbor search. | Frank Seide |
| 1994 | ICASSP | Non-linear regression based feature extraction for connected-word recognition in noise. | Frank Seide, Alfred Mertins |