SK
Sanjeev Khudanpur
eess.AScs.CLcs.SDcs.LGcs.AIcs.CRcs.CVClinical Competencecs.NEGestures
On Valency
published · living versionsW_raacqkk3·v1 · currentpublished
Partially Edited Audio: Generation, Defense, and Open Problems
with Lin Zhang, You Zhang, Nicholas Evans, Xin Wang +5
1 version
Preprints & journals
100 papers in the corpus · 2005–2026Encoder-Free Multimodal LLMs Learn Implicit Encoders2610.24239v1 · David Harwath, Desh Raj, Xavier Velez et al.2026 · 0 citationsarXiv
ASSET: Adaptive Speech Segmentation via Reinforcement Learning2610.14309v1 · Cihan Xiao, Yuan Tseng, Matthew Wiesner et al.2026 · 0 citationsarXiv
All In Good Time: Causality-Aware Framework for LLM-Based Simultaneous Speech-to-Speech Translation2609.30416v1 · Amir Hussein, Enas Albasiri, Travis M. Bartley et al.2026 · 0 citationsarXiv
LAYERSCOPE: A Layerwise Characterization of Video and Multimodal Learned Representations2609.28086v2 · Sandra Arcos-Holzinger, Debashish Chakraborty, Rohita Mocharla et al.2026 · 0 citationsarXiv
Clustering Unsupervised Representations as Defense against Poisoning Attacks on Speech Commands Classification System2606.28953v1 · Thomas Thebaud, Sonal Joshi, Henry Li et al.2026 · 1 citationarXiv
Escape the Language Prior: Mitigating Late-Stage Modality Collapse in Audio Reasoning via Modality-Aware Policy Optimization2605.27741v2 · Cihan Xiao, Yiwen Shao, Chenxing Li et al.2026 · 0 citationsarXiv
Dimensionality-Aware Anomaly Detection in Learned Representations of Self-Supervised Speech Models2605.02715v1 · Sandra Arcos-Holzinger, Sarah M. Erfani, James Bailey et al.2026 · 0 citationsarXiv
Modeling Overlapped Speech with Shuffles2603.17769v1 · Matthew Wiesner, Samuele Cornell, Alexander Polok et al.2026 · 0 citationsarXiv
Can LLMs Help Localize Fake Words in Partially Fake Speech?2603.11205v1 · Lin Zhang, Thomas Thebaud, Zexin Cai et al.2026 · 0 citationsarXiv
Universal Speech Content Factorization2603.08977v2 · Henry Li Xinyuan, Zexin Cai, Lin Zhang et al.2026 · 0 citationsarXiv
SE-DiCoW: Self-Enrolled Diarization-Conditioned Whisper2601.19194v1 · Alexander Polok, Dominik Klement, Samuele Cornell et al.2026 · 1 citationarXiv
SpatialEmb: Extract and Encode Spatial Information for 1-Stage Multi-channel Multi-speaker ASR on Arbitrary Microphone Arrays2601.18037v1 · Yiwen Shao, Yong Xu, Sanjeev Khudanpur et al.2026 · 1 citationarXiv
WST: Weakly Supervised Transducer for Automatic Speech Recognition2511.04035v1 · Dongji Gao, Chenda Liao, Changliang Liu et al.2025 · 0 citationsarXiv
Unsupervised Speech Enhancement using Data-defined Priors2509.22942v1 · Dominik Klement, Matthew Maciejewski, Sanjeev Khudanpur et al.2025 · 0 citationsarXiv
Whisper-UT: A Unified Translation Framework for Speech and Text2509.16375v1 · Cihan Xiao, Matthew Wiesner, Debashish Chakraborty et al.2025 · 0 citationsarXiv
CS-FLEURS: A Massively Multilingual and Code-Switched Speech Dataset2509.14161v1 · Brian Yan, Injy Hamed, Shuichiro Shimizu et al.2025 · 2 citationsarXiv
Scalable Controllable Accented TTS2508.07426v1 · Henry Li Xinyuan, Zexin Cai, Ashi Garg et al.2025 · 0 citationsarXiv
HENT-SRT: Hierarchical Efficient Neural Transducer with Self-Distillation for Joint Speech Recognition and Translation2506.02157v1 · Amir Hussein, Cihan Xiao, Matthew Wiesner et al.2025 · 0 citationsarXiv
CASPER: A Large Scale Spontaneous Speech Dataset2506.00267v3 · Cihan Xiao, Ruixing Liang, Xiangyu Zhang et al.2025 · 0 citationsarXiv
ShiftySpeech: A Large-Scale Synthetic Speech Dataset with Distribution Shifts2502.05674v4 · Ashi Garg, Zexin Cai, Lin Zhang et al.2025 · 0 citationsarXiv
GenVC: Self-Supervised Zero-Shot Voice Conversion2502.04519v2 · Zexin Cai, Henry Li Xinyuan, Ashi Garg et al.2025 · 3 citationsarXiv
DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition2501.00114v1 · Alexander Polok, Dominik Klement, Martin Kocour et al.2024 · 12 citationsarXiv
Target Speaker ASR with Whisper2409.09543v2 · Alexander Polok, Dominik Klement, Matthew Wiesner et al.2024 · 9 citationsarXiv
HLTCOE JHU Submission to the Voice Privacy Challenge 20242409.08913v2 · Henry Li Xinyuan, Zexin Cai, Ashi Garg et al.2024 · 9 citationsarXiv
Clean Label Attacks against SLU Systems2409.08985v1 · Henry Li Xinyuan, Sonal Joshi, Thomas Thebaud et al.2024 · 1 citationarXiv
Privacy versus Emotion Preservation Trade-offs in Emotion-Preserving Speaker Anonymization2409.03655v1 · Zexin Cai, Henry Li Xinyuan, Ashi Garg et al.2024 · 8 citationsarXiv
Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation2407.10303v1 · Ruizhe Huang, Mahsa Yarmohammadi, Sanjeev Khudanpur et al.2024 · 11 citationsarXiv
Benchmarking Language Model Creativity: A Case Study on Code Generation2407.09007v2 · Yining Lu, Dixuan Wang, Tianjian Li et al.2024 · 5 citationsarXiv
Multi-Channel Multi-Speaker ASR Using Target Speaker's Solo Segment2406.09589v2 · Yiwen Shao, Shi-Xiong Zhang, Yong Xu et al.2024 · 3 citationsarXiv
Acoustic modeling for Overlapping Speech Recognition: JHU Chime-5 Challenge System2405.11078v1 · Vimal Manohar, Szu-Jui Chen, Zhiqi Wang et al.2024 · 19 citationsICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, 2019, pp. 6665-6669
Kreyòl-MT: Building MT for Latin American, Caribbean and Colonial African Creole Languages2405.05376v2 · Nathaniel R. Robinson, Raj Dabre, Ammon Shurtz et al.2024 · 0 citationsarXiv
Less Peaky and More Accurate CTC Forced Alignment by Label Priors2406.02560v3 · Ruizhe Huang, Xiaohui Zhang, Zhaoheng Ni et al.2024 · 11 citationsarXiv
On Speaker Attribution with SURT2401.15676v1 · Desh Raj, Matthew Wiesner, Matthew Maciejewski et al.2024 · 1 citationarXiv
Enhancing Code-switching Speech Recognition with Interactive Language Biases2309.16953v1 · Hexin Liu, Leibny Paola Garcia, Xiangyu Zhang et al.2023 · 24 citationsarXiv
Speech collage: code-switched audio generation by collaging monolingual corpora2309.15674v1 · Amir Hussein, Dorsa Zeinali, Ondrej Klejch et al.2023 · 2 citationsarXiv
Enhancing End-to-End Conversational Speech Translation Through Target Language Context Utilization2309.15686v1 · Amir Hussein, Brian Yan, Antonios Anastasopoulos et al.2023 · 4 citationsarXiv
Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition2309.15796v1 · Dongji Gao, Hainan Xu, Desh Raj et al.2023 · 9 citationsarXiv
The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarios2306.13734v2 · Samuele Cornell, Matthew Wiesner, Shinji Watanabe et al.2023 · 57 citationsarXiv
HK-LegiCoST: Leveraging Non-Verbatim Transcripts for Speech Translation2306.11252v2 · Cihan Xiao, Henry Li Xinyuan, Jinyi Yang et al.2023 · 2 citationsarXiv
SURT 2.0: Advances in Transducer-based Multi-talker Speech Recognition2306.10559v2 · Desh Raj, Daniel Povey, Sanjeev Khudanpur2023 · 9 citationsarXiv
Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts2306.01031v1 · Dongji Gao, Matthew Wiesner, Hainan Xu et al.2023 · 9 citationsarXiv
MERLIon CCS Challenge Evaluation Plan2305.19493v1 · Leibny Paola Garcia Perera, Y.H. Victoria Chua, Hexin Liu et al.2023 · 3 citationsarXiv
MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization2305.18881v1 · Victoria Y. H. Chua, Hexin Liu, Leibny Paola Garcia Perera et al.2023 · 10 citationsarXiv
Investigating model performance in language identification: beyond simple error statistics2305.18925v1 · Suzy J. Styles, Victoria Y. H. Chua, Fei Ting Woon et al.2023 · 1 citationarXiv
GPU-accelerated Guided Source Separation for Meeting Transcription2212.05271v2 · Desh Raj, Daniel Povey, Sanjeev Khudanpur2022 · 28 citationsarXiv
EURO: ESPnet Unsupervised ASR Open-source Toolkit2211.17196v3 · Dongji Gao, Jiatong Shi, Shun-Po Chuang et al.2022 · 7 citationsarXiv
Adapting self-supervised models to multi-talker speech recognition using speaker embeddings2211.00482v1 · Zili Huang, Desh Raj, Paola Garc'ia et al.2022 · 30 citationsarXiv
Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization2210.14567v1 · Hexin Liu, Haihua Xu, Leibny Paola Garcia et al.2022 · 30 citationsarXiv
Defense against Adversarial Attacks on Hybrid Speech Recognition using Joint Adversarial Fine-tuning with Denoiser2204.03851v1 · Sonal Joshi, Saurabh Kataria, Yiwen Shao et al.2022 · 3 citationsarXiv
PHO-LID: A Unified Model Incorporating Acoustic-Phonetic and Phonotactic Information for Language Identification2203.12366v2 · Hexin Liu, Leibny Paola Garcia Perera, Andy W. H. Khong et al.2022 · 13 citationsarXiv
Career total: 418 works. 100 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.