Geoffrey Zweig

Computer Science · Physical Sciences

45h-index14.2kcitations171works6.02yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech Recognition and Synthesis(111), Natural Language Processing Techniques(67), Music and Audio Processing(55), Speech and Audio Processing(54), Topic Modeling(46)

Publications170 total

Improving Rnn Transducer Based Asr With Auxiliary Tasks
IEEE RESOURCE CENTERS·2024· 6 citedOpen Access
Kaizen: Continuously Improving Teacher Using Exponential Moving Average for Semi-Supervised Speech Recognition
2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)·2021· 1 citedOpen Access
On Compositions of Transformations in Contrastive Self-Supervised Learning
2021 IEEE/CVF International Conference on Computer Vision (ICCV)·2021· 47 cited
Kaizen: Continuously improving teacher using Exponential Moving Average\n for semi-supervised speech recognition
arXiv (Cornell University)·2021· 1 citedOpen Access
Multi-modal Self-Supervision from Generalized Data Transformations
arXiv (Cornell University)·2021· 119 citedOpen Access
Improving RNN Transducer Based ASR with Auxiliary Tasks
2021· 35 cited
Benchmarking LF-MMI, CTC And RNN-T Criteria For Streaming ASR
2021· 21 cited
Benchmarking LF-MMI, CTC and RNN-T Criteria for Streaming ASR
arXiv (Cornell University)·2020Open Access
Improving RNN Transducer Based ASR with Auxiliary Tasks
arXiv (Cornell University)·2020· 1 citedOpen Access
Large Scale Weakly and Semi-Supervised Learning for Low-Resource Video ASR
2020Open Access
Faster, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces
2020· 32 cited
Contextualizing ASR Lattice Rescoring with Hybrid Pointer Network Language Model
2020· 16 cited
Contextual RNN-T for Open Domain ASR
2020· 5 citedOpen Access
Faster, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces
arXiv (Cornell University)·2020· 2 citedOpen Access
Contextualizing ASR Lattice Rescoring with Hybrid Pointer Network Language Model
arXiv (Cornell University)·2020· 5 citedOpen Access
Large scale weakly and semi-supervised learning for low-resource video\n ASR
arXiv (Cornell University)·2020Open Access
Multilingual Graphemic Hybrid ASR with Massive Data Augmentation.
Workshop Spoken Language Technologies for Under-resourced Languages·2020· 9 cited
DEJA-VU: Double Feature Presentation and Iterated Loss in Deep Transformer Networks
2020· 1 citedOpen Access
Training ASR Models By Generation of Contextual Information
2020· 4 citedOpen Access
Transformer-Based Acoustic Modeling for Hybrid Speech Recognition
2020· 253 citedOpen Access
page 1 of 9Next →

Frequent Co-authors

Dong Yu(11), Kaisheng Yao(8), Jasha Droppo(7), George Saon(7), Andreas Stolcke(6), Daniel Povey(6), Li Deng(5), Xiaodong He(5), Frank Seide(5), Brian Kingsbury(5), Lidia Mangu(5), Wen-tau Yih(4), Hao Fang(4), Saurabh Gupta(4), Margaret Mitchell(4), John Platt(4), Wayne Xiong(4), Xuedong Huang(4), Baolin Peng(4), Michael L. Seltzer(4)