Yassir Fathullah

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 28

Top Topics

Transfer Learning

Speech Recognition

Error Correction

Top Venues

Publications

Adian Liusie, Vatsal Raina, Yassir Fathullah, Mark J. F. Gales
Efficient LLM Comparative Assessment: a Product of Experts Framework for Pairwise Comparisons. CoRR (2024)
Yassir Fathullah, Mark J. F. Gales
Efficient Sample-Specific Encoder Perturbations. CoRR (2024)
Yassir Fathullah, Chunyang Wu, Egor Lakomkin, Ke Li, Junteng Jia, Yuan Shangguan, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer
AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs. NAACL-HLT (2024)
Egor Lakomkin, Chunyang Wu, Yassir Fathullah, Ozlem Kalinli, Michael L. Seltzer, Christian Fuegen
End-to-End Speech Recognition Contextualization with Large Language Models. ICASSP (2024)
Yuan Shangguan, Haichuan Yang, Danni Li, Chunyang Wu, Yassir Fathullah, Dilin Wang, Ayushi Dalmia, Raghuraman Krishnamoorthi, Ozlem Kalinli, Junteng Jia, Jay Mahadeokar, Xin Lei, Mike Seltzer, Vikas Chandra
TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-Device ASR Models. ICASSP (2024)
Adian Liusie, Yassir Fathullah, Mark J. F. Gales
Teacher-Student Training for Debiasing: General Permutation Debiasing for Large Language Models. CoRR (2024)
Adian Liusie, Yassir Fathullah, Mark J. F. Gales
Teacher-Student Training for Debiasing: General Permutation Debiasing for Large Language Models. ACL (Findings) (2024)
Yassir Fathullah, Chunyang Wu, Egor Lakomkin, Junteng Jia, Yuan Shangguan, Ke Li, Jinxi Guo, Wenhan Xiong, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer
Prompting Large Language Models with Speech Recognition Abilities. ICASSP (2024)
Rao Ma, Yassir Fathullah, Mengjie Qian, Siyuan Tang, Mark J. F. Gales, Kate M. Knill
Cross-Lingual Transfer Learning for Speech Translation. CoRR (2024)
Yassir Fathullah, Puria Radmard, Adian Liusie, Mark J. F. Gales
Who Needs Decoders? Efficient Estimation of Sequence-Level Attributes with Proxies. EACL (1) (2024)
Yassir Fathullah, Chunyang Wu, Yuan Shangguan, Junteng Jia, Wenhan Xiong, Jay Mahadeokar, Chunxi Liu, Yangyang Shi, Ozlem Kalinli, Mike Seltzer, Mark J. F. Gales
Multi-Head State Space Model for Speech Recognition. INTERSPEECH (2023)
Yuan Shangguan, Haichuan Yang, Danni Li, Chunyang Wu, Yassir Fathullah, Dilin Wang, Ayushi Dalmia, Raghuraman Krishnamoorthi, Ozlem Kalinli, Junteng Jia, Jay Mahadeokar, Xin Lei, Mike Seltzer, Vikas Chandra
TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models. CoRR (2023)
Yassir Fathullah, Puria Radmard, Adian Liusie, Mark J. F. Gales
Who Needs Decoders? Efficient Estimation of Sequence-level Attributes. CoRR (2023)
Yassir Fathullah, Guoxuan Xia, Mark J. F. Gales
Logit-based ensemble distribution distillation for robust autoregressive sequence uncertainties. UAI (2023)
Egor Lakomkin, Chunyang Wu, Yassir Fathullah, Ozlem Kalinli, Michael L. Seltzer, Christian Fuegen
End-to-End Speech Recognition Contextualization with Large Language Models. CoRR (2023)
Yassir Fathullah, Chunyang Wu, Yuan Shangguan, Junteng Jia, Wenhan Xiong, Jay Mahadeokar, Chunxi Liu, Yangyang Shi, Ozlem Kalinli, Mike Seltzer, Mark J. F. Gales
Multi-Head State Space Model for Speech Recognition. CoRR (2023)
Yassir Fathullah, Chunyang Wu, Egor Lakomkin, Junteng Jia, Yuan Shangguan, Ke Li, Jinxi Guo, Wenhan Xiong, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer
Prompting Large Language Models with Speech Recognition Abilities. CoRR (2023)
Yassir Fathullah, Chunyang Wu, Egor Lakomkin, Junteng Jia, Yuan Shangguan, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer
Towards General-Purpose Speech Abilities for Large Language Models Using Unpaired Data. CoRR (2023)
Potsawee Manakul, Yassir Fathullah, Adian Liusie, Vyas Raina, Vatsal Raina, Mark J. F. Gales
CUED at ProbSum 2023: Hierarchical Ensemble of Summarization Models. CoRR (2023)
Potsawee Manakul, Yassir Fathullah, Adian Liusie, Vyas Raina, Vatsal Raina, Mark J. F. Gales
CUED at ProbSum 2023: Hierarchical Ensemble of Summarization Models. BioNLP@ACL (2023)
Yassir Fathullah, Guoxuan Xia, Mark J. F. Gales
Logit-Based Ensemble Distribution Distillation for Robust Autoregressive Sequence Uncertainties. CoRR (2023)
Yassir Fathullah, Mark J. F. Gales
Self-distribution distillation: efficient uncertainty estimation. UAI (2022)
Yassir Fathullah, Mark J. F. Gales
Self-Distribution Distillation: Efficient Uncertainty Estimation. CoRR (2022)
Puria Radmard, Yassir Fathullah, Aldo Lipani
Subsequence Based Deep Active Learning for Named Entity Recognition. ACL/IJCNLP (1) (2021)
Yassir Fathullah, M. J. F. Gales, Andrey Malinin
Ensemble Distillation Approaches for Grammatical Error Correction. ICASSP (2021)
Yassir Fathullah, Chao Zhang, Philip C. Woodland
Improved Large-Margin Softmax Loss for Speaker Diarisation. ICASSP (2020)
Yassir Fathullah, Mark J. F. Gales, Andrey Malinin
Ensemble Distillation Approaches for Grammatical Error Correction. CoRR (2020)
Yassir Fathullah, Chao Zhang, Philip C. Woodland
Improved Large-margin Softmax Loss for Speaker Diarisation. CoRR (2019)