Title |
|---|
 HiFi-Stream: Streaming Speech Enhancement with Generative Adversarial NetworksIEEE Signal Processing Letters (IEEE SPL), 2025 |
 Anchored Speech Recognition with Neural TransducersIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022 |
 Closing the Gap between Single-User and Multi-User VoiceFilter-LiteThe Speaker and Language Recognition Workshop (Odyssey), 2022 |
 Cross-attention conformer for context modeling in speech enhancement for
ASRAutomatic Speech Recognition & Understanding (ASRU), 2021 |
 Turn-to-Diarize: Online Speaker Diarization Constrained by Transformer
Transducer Speaker Turn DetectionIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021 |
