4 accepted papers
Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extensively annotated parallel audio-text data, which are labor-intensive. We introduce a parallel-data-free training scheme,…
Active reconfigurable intelligent surface (RIS) is a new RIS architecture that can reflect and amplify communication signals. It can provide enhanced performance gain compared to the conventional passive RIS systems that can only reflect the signals. On the other hand, the design problem of active R…
Target-speaker automatic speech recognition (ASR) aims to transcribe the desired speech of a target speaker from multi-talker overlapped utterances. Most of the existing target-speaker ASR (TS-ASR) methods involve either training from scratch or fully finetuning a pre-trained model, leading to signi…
We propose a frame rate up-conversion method with quadruple motion vector post-processing scheme (QMVPS). By considering occlusion and hole problems, we adopt the hybrid motion estimation (ME) method which is a combination of bilateral ME and unilateral ME in both directions. To produce better quali…