Frank Seide

Publication Activity (10 Years)

Years Active: 1994-2024
Publications (10 Years): 24

Top Topics

Speech Recognition

Stochastic Gradient Descent

Automatic Speech Recognition

Top Venues

Publications

Jinxi Guo, Niko Moritz, Yingyi Ma, Frank Seide, Chunyang Wu, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer
Effective internal language model training and fusion for factorized transducer model. CoRR (2024)
Frank Seide, Morrie Doulaty, Yangyang Shi, Yashesh Gaur, Junteng Jia, Chunyang Wu
Speech ReaLLM - Real-time Streaming Speech Recognition with Multimodal LLMs by Teaching the Flow of Time. CoRR (2024)
Ju Lin, Niko Moritz, Yiteng Huang, Ruiming Xie, Ming Sun, Christian Fuegen, Frank Seide
AGADIR: Towards Array-Geometry Agnostic Directional Speech Recognition. CoRR (2024)
Ju Lin, Niko Moritz, Yiteng Huang, Ruiming Xie, Ming Sun, Christian Fuegen, Frank Seide
AGADIR: Towards Array-Geometry Agnostic Directional Speech Recognition. ICASSP (2024)
Rastislav Rabatin, Frank Seide, Ernie Chang
Navigating the Minefield of MT Beam Search in Cascaded Streaming Speech Translation. CoRR (2024)
Jinxi Guo, Niko Moritz, Yingyi Ma, Frank Seide, Chunyang Wu, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer
Effective Internal Language Model Training and Fusion for Factorized Transducer Model. ICASSP (2024)
Tiantian Feng, Ju Lin, Yiteng Huang, Weipeng He, Kaustubh Kalgaonkar, Niko Moritz, Li Wan, Xin Lei, Ming Sun, Frank Seide
Directional Source Separation for Robust Speech Recognition on Smart Glasses. CoRR (2023)
Junteng Jia, Ke Li, Mani Malek, Kshitiz Malik, Jay Mahadeokar, Ozlem Kalinli, Frank Seide
Joint Federated Learning and Personalization for on-Device ASR. ASRU (2023)
Ju Lin, Niko Moritz, Ruiming Xie, Kaustubh Kalgaonkar, Christian Fuegen, Frank Seide
Directional Speech Recognition for Speaker Disambiguation and Cross-talk Suppression. INTERSPEECH (2023)
Duc Le, Frank Seide, Yuhao Wang, Yang Li, Kjell Schubert, Ozlem Kalinli, Michael L. Seltzer
Factorized Blank Thresholding for Improved Runtime Efficiency of Neural Transducers. ICASSP (2023)
Mei-Yuh Hwang, Yangyang Shi, Ankit Ramchandani, Guan Pang, Praveen Krishnan, Lucas Kabela, Frank Seide, Samyak Datta, Jun Liu
DISGO: Automatic End-to-End Evaluation for Scene Text OCR. CoRR (2023)
Duc Le, Frank Seide, Yuhao Wang, Yang Li, Kjell Schubert, Ozlem Kalinli, Michael L. Seltzer
Factorized Blank Thresholding for Improved Runtime Efficiency of Neural Transducers. CoRR (2022)
Junteng Jia, Jay Mahadeokar, Weiyi Zheng, Yuan Shangguan, Ozlem Kalinli, Frank Seide
Federated Domain Adaptation for ASR with Full Self-Supervision. CoRR (2022)
Junteng Jia, Jay Mahadeokar, Weiyi Zheng, Yuan Shangguan, Ozlem Kalinli, Frank Seide
Federated Domain Adaptation for ASR with Full Self-Supervision. INTERSPEECH (2022)
Niko Moritz, Frank Seide, Duc Le, Jay Mahadeokar, Christian Fuegen
An Investigation of Monotonic Transducers for Large-Scale Automatic Speech Recognition. SLT (2022)
Niko Moritz, Frank Seide, Duc Le, Jay Mahadeokar, Christian Fuegen
An Investigation of Monotonic Transducers for Large-Scale Automatic Speech Recognition. CoRR (2022)
Hany Hassan, Anthony Aue, Chang Chen, Vishal Chowdhary, Jonathan Clark, Christian Federmann, Xuedong Huang, Marcin Junczys-Dowmunt, William Lewis, Mu Li, Shujie Liu, Tie-Yan Liu, Renqian Luo, Arul Menezes, Tao Qin, Frank Seide, Xu Tan, Fei Tian, Lijun Wu, Shuangzhi Wu, Yingce Xia, Dongdong Zhang, Zhirui Zhang, Ming Zhou
Achieving Human Parity on Automatic Chinese to English News Translation. CoRR (2018)
Marcin Junczys-Dowmunt, Roman Grundkiewicz, Tomasz Dwojak, Hieu Hoang, Kenneth Heafield, Tom Neckermann, Frank Seide, Ulrich Germann, Alham Fikri Aji, Nikolay Bogoychev, André F. T. Martins, Alexandra Birch
Marian: Fast Neural Machine Translation in C++. CoRR (2018)
Marcin Junczys-Dowmunt, Roman Grundkiewicz, Tomasz Dwojak, Hieu Hoang, Kenneth Heafield, Tom Neckermann, Frank Seide, Ulrich Germann, Alham Fikri Aji, Nikolay Bogoychev, André F. T. Martins, Alexandra Birch
Marian: Fast Neural Machine Translation in C++. ACL (4) (2018)
Wayne Xiong, Jasha Droppo, Xuedong Huang, Frank Seide, Mike Seltzer, Andreas Stolcke, Dong Yu, Geoffrey Zweig
The microsoft 2016 conversational speech recognition system. ICASSP (2017)
Wayne Xiong, Jasha Droppo, Xuedong Huang, Frank Seide, Michael L. Seltzer, Andreas Stolcke, Dong Yu, Geoffrey Zweig
Toward Human Parity in Conversational Speech Recognition. IEEE ACM Trans. Audio Speech Lang. Process. 25 (12) (2017)
Frank Seide, Amit Agarwal
CNTK: Microsoft's Open-Source Deep-Learning Toolkit. KDD (2016)
Wayne Xiong, Jasha Droppo, Xuedong Huang, Frank Seide, Mike Seltzer, Andreas Stolcke, Dong Yu, Geoffrey Zweig
Achieving Human Parity in Conversational Speech Recognition. CoRR (2016)
Wayne Xiong, Jasha Droppo, Xuedong Huang, Frank Seide, Mike Seltzer, Andreas Stolcke, Dong Yu, Geoffrey Zweig
The Microsoft 2016 Conversational Speech Recognition System. CoRR (2016)
Abdel-rahman Mohamed, Frank Seide, Dong Yu, Jasha Droppo, Andreas Stolcke, Geoffrey Zweig, Gerald Penn
Deep bi-directional recurrent networks over spectral windows. ASRU (2015)
Frank Seide, Hao Fu, Jasha Droppo, Gang Li, Dong Yu
On parallelizability of stochastic gradient descent for speech DNNS. ICASSP (2014)
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
An introduction to computational networks and the computational network toolkit (invited talk). INTERSPEECH (2014)
Frank Seide, Hao Fu, Jasha Droppo, Gang Li, Dong Yu
1-bit stochastic gradient descent and its application to data-parallel distributed training of speech DNNs. INTERSPEECH (2014)
Anthony Aue, Qin Gao, Hany Hassan, Xiaodong He, Gang Li, Nicholas Ruiz, Frank Seide
MSR-FBK IWSLT 2013 SLT system description. IWSLT (Evaluation Campaign) (2013)
Hang Su, Gang Li, Dong Yu, Frank Seide
Error back propagation for sequence training of Context-Dependent Deep NetworkS for conversational speech transcription. ICASSP (2013)
Dong Yu, Michael L. Seltzer, Jinyu Li, Jui-Ting Huang, Frank Seide
Feature Learning in Deep Neural Networks - A Study on Speech Recognition Tasks ICLR (2013)
Xinjian Zhang, Lijuan Wang, Gang Li, Frank Seide, Frank K. Soong
A new language independent, photo-realistic talking head driven by voice only. INTERSPEECH (2013)
Dong Yu, Li Deng, Frank Seide
The Deep Tensor Neural Network With Applications to Large Vocabulary Speech Recognition. IEEE Trans. Speech Audio Process. 21 (2) (2013)
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
Recent advances in deep learning for speech research at Microsoft. ICASSP (2013)
Dong Yu, Kaisheng Yao, Hang Su, Gang Li, Frank Seide
KL-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition. ICASSP (2013)
Xie Chen, Adam Eversole, Gang Li, Dong Yu, Frank Seide
Pipelined Back-Propagation for Context-Dependent Deep Neural Networks. INTERSPEECH (2012)
Frank Seide, Sean McDirmid
ClippyScript: A Programming Language for Multi-Domain Dialogue Systems. INTERSPEECH (2012)
Dong Yu, Frank Seide, Gang Li
Conversational Speech Transcription Using Context-Dependent Deep Neural Networks. ICML (2012)
Dong Yu, Frank Seide, Gang Li, Li Deng
Exploiting sparseness in deep neural networks for large vocabulary speech recognition. ICASSP (2012)
Kit Thambiratnam, Weiwu Zhu, Frank Seide
Voice Activity Detection Using Speech Recognizer Feedback. INTERSPEECH (2012)
Kaisheng Yao, Dong Yu, Frank Seide, Hang Su, Li Deng, Yifan Gong
Adaptation of context-dependent deep neural networks for automatic speech recognition. SLT (2012)
Gang Li, Huifeng Zhu, Gong Cheng, Kit Thambiratnam, Behrooz Chitsaz, Dong Yu, Frank Seide
Context-dependent Deep Neural Networks for audio indexing of real-life data. SLT (2012)
Dong Yu, Li Deng, Frank Seide
Large Vocabulary Speech Recognition Using Deep Tensor Neural Networks. INTERSPEECH (2012)
Frank Seide, Gang Li, Xie Chen, Dong Yu
Feature engineering in Context-Dependent Deep Neural Networks for conversational speech transcription. ASRU (2011)
Frank Seide, Gang Li, Dong Yu
Conversational Speech Transcription Using Context-Dependent Deep Neural Networks. INTERSPEECH (2011)
Timo Mertens, Kit Thambiratnam, Frank Seide
Subword-based multi-span pronunciation adaptation for recognizing accented speech. ASRU (2011)
Kishan Thambiratnam, Gang Li, Sha Meng, Frank Seide
Leveraging the Web for automatically generating indexable and browsable keywords for speech files. ICASSP (2011)
Frank Seide, Pei Zhao
On using missing-feature theory with cepstral features - approximations to the multivariate integral. INTERSPEECH (2010)
Qian Lin, Lie Lu, Christopher Weare, Frank Seide
Music rhythm characterization with application to workout-mix generation. ICASSP (2010)
Sha Meng, Kishan Thambiratnam, Yimeng Lin, Lifang Wang, Gang Li, Frank Seide
Vocabulary and language model adaptation using just one speech file. ICASSP (2010)
Kishan Thambiratnam, Frank Seide
Unsupervised lattice-based acoustic model adaptation for speaker-dependent conversational telephone speech transcription. INTERSPEECH (2009)
Frank Seide, Kit Thambiratnam, Lie Lu, Roger Peng Yu
Multimedia retrieval through indexing speech: an enterprise perspective. SSCS@MM (2009)
R. Wallace, Kishan Thambiratnam, Frank Seide
Unsupervised speaker adaptation for telephone call transcription. ICASSP (2009)
Wenzhu Shen, Roger Peng Yu, Frank Seide, Ji Wu
Automatic punctuation generation for speech. ASRU (2009)
Linxing Xiao, Lie Lu, Frank Seide, Jie Zhou
Learning a music similarity measure on automatic annotations with application to playlist generation. ICASSP (2009)
Lie Lu, Frank Seide
Mobile ringtone search through query by humming. ICASSP (2008)
Xing Xie, Lie Lu, Menglei Jia, Hua Li, Frank Seide, Wei-Ying Ma
Mobile Search With Multimodal Queries. Proc. IEEE 96 (4) (2008)
Kishan Thambiratnam, Frank Seide
Fragmented context-dependent syllable acoustic models. INTERSPEECH (2008)
Frank Seide, Kishan Thambiratnam, Roger Peng Yu
Word-lattice based spoken-document indexing with standard text indexers. SLT (2008)
Sha Meng, Jian Shao, Roger Peng Yu, Jia Liu, Frank Seide
Addressing the out-of-vocabulary problem for large-scale Chinese spoken term detection. INTERSPEECH (2008)
Peng Yu, Yu Shi, Frank Seide
Approximateword-lattice indexing with text indexers: Time-Anchored Lattice Expansion. ICASSP (2008)
Jian Shao, Roger Peng Yu, Qingwei Zhao, Yonghong Yan, Frank Seide
Towards vocabulary-independent speech indexing for large-scale repositories. INTERSPEECH (2008)
Yu Shi, Frank Seide, Frank K. Soong
GPU-accelerated Gaussian clustering for fMPE discriminative training. INTERSPEECH (2008)
Sha Meng, Peng Yu, Jia Liu, Frank Seide
Fusing multiple systems into a compact lattice index for chinese spoken term detection. ICASSP (2008)
Peng Yu, Jie Xu, Guo-Liang Zhang, Yuchou Chang, Frank Seide
A Hidden-State Maximum Entropy Model Forword Confidence Estimation. ICASSP (4) (2007)
Frank Seide, Peng Yu, Yu Shi
Towards spoken-document retrieval for the enterprise: Approximate word-lattice indexing with text indexers. ASRU (2007)
Sha Meng, Peng Yu, Frank Seide, Jia Liu
A study of lattice-based spoken term detection for Chinese spontaneous speech. ASRU (2007)
C. E. Liu, Kishan Thambiratnam, Frank Seide
Online vocabulary adaptation using limited adaptation data. INTERSPEECH (2007)
Kishan Thambiratnam, Frank Seide
Learning spoken document similarity and recommendation using supervised probabilistic latent semantic analysis. INTERSPEECH (2007)
Kishan Thambiratnam, Frank Seide, Peng Yu
Discriminatively Trained spoken Document Similarity Models and their Application to Probabilistic Latent Semantic Analysis. SLT (2006)
Peng Yu, Duo Zhang, Frank Seide
Maximum Entropy Based Normalization Of Word Posteriors For Phonetic And Lvcsr Lattice Search. ICASSP (1) (2006)
Zheng-Yu Zhou, Peng Yu, Ciprian Chelba, Frank Seide
Towards Spoken-Document Retrieval for the Internet: Lattice Indexing For Large-Scale Web-Search Architectures. HLT-NAACL (2006)
Peng Yu, Kaijiang Chen, Lie Lu, Frank Seide
Searching the Audio Notebook: Keyword Search in Recorded Conversation. HLT/EMNLP (2005)
Frank Seide
The use of virtual hypothesis copies in decoding of large-vocabulary continuous speech. IEEE Trans. Speech Audio Process. 13 (4) (2005)
Peng Yu, Kaijiang Chen, Chengyuan Ma, Frank Seide
Vocabulary-Independent Indexing of Spontaneous Speech. IEEE Trans. Speech Audio Process. 13 (5-1) (2005)
Peng Yu, Frank Seide
Fast Two-Stage Vocabulary-Independent Search In Spontaneous Speech. ICASSP (1) (2005)
Frank Seide, Peng Yu, Chengyuan Ma, Eric Chang
Vocabulary-independent search in spontaneous speech. ICASSP (1) (2004)
Peng Yu, Frank Seide, Chengyuan Ma, Eric Chang
An improved model-based speaker segmentation system. INTERSPEECH (2003)
Frank Seide, Jian-Lai Zhou, Li Deng
Coarticulation modeling by embedding a target-directed hidden trajectory model into HMM - MAP decoding and evaluation. ICASSP (1) (2003)
Jian-Lai Zhou, Frank Seide, Li Deng
Coarticulation modeling by embedding a target-directed hidden trajectory model into HMM - model and training. ICASSP (1) (2003)
Eric Chang, Frank Seide, Helen M. Meng, Zhuoran Chen, Yu Shi, Yuk-Chi Li
A system for spoken query information retrieval on mobile devices. IEEE Trans. Speech Audio Process. 10 (8) (2002)
Nick J.-C. Wang, Sammy S.-M. Lee, Frank Seide, Lin-Shan Lee
Rapid speaker adaptation using a priori knowledge by eigenspace analysis of MLLR parameters. ICASSP (2001)
Bernd Souvignier, Andreas Kellner, Bernhard Rueber, Hauke Schramm, Frank Seide
The thoughtful elephant: strategies for spoken dialog systems. IEEE Trans. Speech Audio Process. 8 (1) (2000)
Frank Seide, Nick J.-C. Wang
Two-stream modeling of Mandarin tones. INTERSPEECH (2000)
Yuan-Fu Liao, Nick J.-C. Wang, Max Huang, Hank Huang, Frank Seide
Improvements of the Philips 2000 Taiwan Mandarin benchmark system. INTERSPEECH (2000)
Hank Chang-Han Huang, Frank Seide
Pitch tracking and tone features for Mandarin speech recognition. ICASSP (2000)
Hsiao-Chuan Wang, Frank Seide, Chiu-yu Tseng, Lin-Shan Lee
MAT-2000 - design, collection, and validation of a Mandarin 2000-speaker telephone speech database. INTERSPEECH (2000)
Chiwei Che, Nick J.-C. Wang, Max Huang, Hank Huang, Frank Seide
Development of the philips 1999 taiwan Mandarin benchmark system. EUROSPEECH (1999)
Andreas Kellner, Bernhard Rueber, Frank Seide, Bach-Hiep Tran
PADIS - An automatic telephone switchboard and directory information system. Speech Commun. 23 (1-2) (1997)
Frank Seide, Andreas Kellner
Towards an automated directory information system. EUROSPEECH (1997)
Stefan Ortmanns, Hermann Ney, Frank Seide, Ingo Lindam
A comparison of time conditioned and word conditioned search techniques for large vocabulary speech recognition. ICSLP (1996)
Frank Seide, Bernhard Rueber, Andreas Kellner
Improving speech understanding by incorporating database constraints and dialogue history. ICSLP (1996)
Bach-Hiep Tran, Frank Seide, Volker Steinbiss
A word graph based n-best search in continuous speech recognition. ICSLP (1996)
Frank Seide
Fast likelihood computation for continuous-mixture densities using a tree-based nearest neighbor search. EUROSPEECH (1995)
Harald Aust, Martin Oerder, Frank Seide, Volker Steinbiss
The Philips automatic train timetable information system. Speech Commun. 17 (3-4) (1995)
Frank Seide, Alfred Mertins
Non-linear regression based feature extraction for connected-word recognition in noise. ICASSP (2) (1994)