Vahid Ahmadi Kalkhorani

12 papers A 3Misc 2Journal 7
YearRankTypeTitle / Venue / Authors
2026 J jnl
Audiovisual speech enhancement and voice activity detection using generative and regressive visual features.
Comput. Speech Lang.
Cheng Yu, Vahid Ahmadi Kalkhorani, Buye Xu, DeLiang Wang
2025 J jnl
AV-CrossNet: An Audiovisual Complex Spectral Mapping Network for Speech Separation by Leveraging Narrow- and Cross-Band Modeling.
IEEE J. Sel. Top. Signal Process.
Vahid Ahmadi Kalkhorani, Cheng Yu, Anurag Kumar, Ke Tan, Buye Xu, DeLiang Wang
2025 Misc conf
Elevating Robust ASR By Decoupling Multi-Channel Speaker Separation and Speech Recognition.
ICASSP
Yufeng Yang, Hassan Taherian, Vahid Ahmadi Kalkhorani, DeLiang Wang
2025 J jnl
Elevating Robust Multi-Talker ASR by Decoupling Speaker Separation and Speech Recognition.
CoRR
Yufeng Yang, Hassan Taherian, Vahid Ahmadi Kalkhorani, DeLiang Wang
2025 A conf
Online AV-CrossNet: a Causal and Efficient Audiovisual System for Speech Enhancement and Target Speaker Extraction.
INTERSPEECH
Cheng Yu, Vahid Ahmadi Kalkhorani, Buye Xu, DeLiang Wang
2024 J jnl
AV-CrossNet: an Audiovisual Complex Spectral Mapping Network for Speech Separation By Leveraging Narrow- and Cross-Band Modeling.
CoRR
Vahid Ahmadi Kalkhorani, Cheng Yu, Anurag Kumar, Ke Tan, Buye Xu, DeLiang Wang
2024 Misc conf
Audiovisual Speaker Separation with Full- and Sub-Band Modeling in the Time-Frequency Domain.
ICASSP
Vahid Ahmadi Kalkhorani, Anurag Kumar, Ke Tan, Buye Xu, DeLiang Wang
2024 J jnl
Beyond the Frame: Single and mutilple video summarization method with user-defined length.
CoRR
Vahid Ahmadi Kalkhorani, Qingquan Zhang, Guanqun Song, Ting Zhu
2024 J jnl
CrossNet: Leveraging Global, Cross-Band, Narrow-Band, and Positional Encoding for Single- and Multi-Channel Speaker Separation.
CoRR
Vahid Ahmadi Kalkhorani, DeLiang Wang
2024 J jnl
TF-CrossNet: Leveraging Global, Cross-Band, Narrow-Band, and Positional Encoding for Single- and Multi-Channel Speaker Separation.
IEEE ACM Trans. Audio Speech Lang. Process.
Vahid Ahmadi Kalkhorani, DeLiang Wang
2024 A conf
Towards Explainable Monaural Speaker Separation with Auditory-based Training.
INTERSPEECH
Hassan Taherian, Vahid Ahmadi Kalkhorani, Ashutosh Pandey, Daniel Wong, Buye Xu, DeLiang Wang
2023 A conf
Time-domain Transformer-based Audiovisual Speaker Separation.
INTERSPEECH
Vahid Ahmadi Kalkhorani, Anurag Kumar, Ke Tan, Buye Xu, DeLiang Wang