Selected Publications

HENT-SRT: Hierarchical Efficient Neural Transducer with Self-Distillation for Joint Speech Recognition and Translation
_{Amir Hussein, Cihan Xiao, Matthew Wiesner, Dan Povey, Leibny Paola Garcia Perera, Sanjeev Khudanpur}
_{Proceedings of the 22th International Conference on Spoken Language Translation (IWSLT), 2025}
_{Best student paper award}
_paper

HASRD: Hierarchical Acoustic and Semantic Representation Disentanglement
_{Amir Hussein, Sameer Khurana, Gordon Wichern, François G. Germain, Jonathan Le Roux}
_{26th Annual Conference of the International Speech Communication Association (INTERSPEECH) 2025}
_paper

Enhancing Neural Transducer for Multilingual ASR with Synchronized Language Diarization
_{Amir Hussein, Desh Raj, Matthew Wiesner, Daniel Povey, Paola Garcia, Sanjeev Khudanpur}
_{25th Annual Conference of the International Speech Communication Association (INTERSPEECH), 2024}
_paper

ENHANCING END-TO-END CONVERSATIONAL SPEECH TRANSLATION THROUGH TARGET LANGUAGE CONTEXT UTILIZATION
_{Amir Hussein, Brian Yan, Antonios Anastasopoulos, Shinji Watanabe, Sanjeev Khudanpur}
_{IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024}
_paper

SPEECH COLLAGE: CODE-SWITCHED AUDIO GENERATION BY COLLAGING MONOLINGUAL CORPORA
_{Amir Hussein, Dorsa Zeinali, Ondrej Klejch, Matthew Wiesner Brian Yan, Shammur Chowdhury, Ahmed Ali, Shinji Watanabe, Sanjeev Khudanpur}
_{IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024}
_paper

JHU IWSLT 2023 Dialect Speech Translation System Description
_{Amir Hussein, Cihan Xiao, Neha Verma, Thomas Thebaud, Matthew Wiesner, Sanjeev Khudanpur}
_{Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT), 2023}
_{Winning second-place in the IWSLT 2023 Dialectal Track}
_paper

JHU IWSLT 2022 Dialect Speech Translation System Description
_{Amir Hussein, Jinyi Yang, Matthew Wiesner, Sanjeev Khudanpur}
_{Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT), 2022}
_{Winning second-place in the IWSLT 2022 Dialectal Track}
_paper

Arabic Speech Recognition by End-to-End, Modular Systems and Human
_{Amir Hussein, Shinji Watanabe,Ahmed Ali}
_{Computer Speech & Language (CSL), 2022}
_paper

For a complete list, see my Google Scholar.