| 2025 | ICASSP | Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and Inference. | Edresson Casanova, Ryan Langman, Paarth Neekhara, Shehzeen Hussain, Jason Li, Subhankar Ghosh, Ante Jukic, Sang-gil Lee |
| 2025 | ICASSP | Modifying Flow Matching for Generative Speech Enhancement. | Roman Korostik, Rauf Nasretdinov, Ante Jukic |
| 2025 | ICASSP | Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration. | Pin-Jui Ku, Alexander H. Liu, Roman Korostik, Sung-Feng Huang, Szu-Wei Fu, Ante Jukic |
| 2025 | ICASSP | Robust Speech Recognition with Schrdinger Bridge-Based Speech Enhancement. | Rauf Nasretdinov, Roman Korostik, Ante Jukic |
| 2025 | Interspeech | NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference. | Edresson Casanova, Paarth Neekhara, Ryan Langman, Shehzeen Hussain, Subhankar Ghosh, Xuesong Yang, Ante Jukic, Jason Li, Boris Ginsburg |
| 2025 | Interspeech | Universal Speech Enhancement with Regression and Generative Mamba. | Rong Chao, Rauf Nasretdinov, Yu-Chiang Frank Wang, Ante Jukic, Szu-Wei Fu, Yu Tsao |
| 2025 | Interspeech | VoiceNoNG: Robust High-Quality Speech Editing Model without Hallucinations. | Sung-Feng Huang, Heng-Cheng Kuo, Zhehuai Chen, Xuesong Yang, Pin-Jui Ku, Ante Jukic, Huck Yang, Yu Tsao, Yu-Chiang Frank Wang, Hung-yi Lee, Szu-Wei Fu |
| 2025 | Interspeech | Unified Semi-Supervised Pipeline for Automatic Speech Recognition. | Nune Tadevosyan, Nikolay Karpov, Andrei Andrusenko, Vitaly Lavrukhin, Ante Jukic |
| 2024 | Interspeech | Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations. | Kunal Dhawan, Nithin Rao Koluguri, Ante Jukic, Ryan Langman, Jagadeesh Balam, Boris Ginsburg |
| 2024 | Interspeech | Schrdinger Bridge for Generative Speech Enhancement. | Ante Jukic, Roman Korostik, Jagadeesh Balam, Boris Ginsburg |
| 2016 | ICASSP | Robust sparsity-promoting acoustic multi-channel equalization for speech dereverberation. | Ina Kodrasi, Ante Jukic, Simon Doclo |
| 2015 | ICASSP | Multi-channel linear prediction-based speech dereverberation with low-rank power spectrogram approximation. | Ante Jukic, Nasser Mohammadiha, Toon van Waterschoot, Timo Gerkmann, Simon Doclo |
| 2014 | ICASSP | Speech dereverberation using weighted prediction error with Laplacian model of the desired signal. | Ante Jukic, Simon Doclo |