24 citations · 97 across the 31 of their papers we have counts for
7 papers · 1 filter
CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos
Hao-Wen Dong, Naoya Takahashi, Yuki Mitsufuji +2
Recent years have seen progress beyond domain-specific sound separation for speech or music towards universal sound separation for arbitrary sounds. Prior work on universal sound s…
Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation
Yusong Wu, Ke Chen, Tianyu Zhang +4
Contrastive learning has shown remarkable success in the field of multimodal representation learning. In this paper, we propose a pipeline of contrastive language-audio pretraining…
Improving Choral Music Separation through Expressive Synthesized Data from Sampled Instruments
Ke Chen, Hao-Wen Dong, Yi Luo +4
Choral music separation refers to the task of extracting tracks of voice parts (e.g., soprano, alto, tenor, and bass) from mixed audio. The lack of datasets has impeded research on…
Multitrack Music Transformer
Hao-Wen Dong, Ke Chen, Shlomo Dubnov +2
Existing approaches for generating multitrack music with transformer models have been limited in terms of the number of instruments, the length of the music segments and slow infer…
Deep Performer: Score-to-Audio Music Performance Synthesis
Hao-Wen Dong, Cong Zhou, Taylor Berg-Kirkpatrick +1
Music performance synthesis aims to synthesize a musical score into a natural performance. In this paper, we borrow recent advances in text-to-speech synthesis and present the Deep…
TONet: Tone-Octave Network for Singing Melody Extraction from Polyphonic Music
Ke Chen, Shuai Yu, Cheng-i Wang +3
Singing melody extraction is an important problem in the field of music information retrieval. Existing methods typically rely on frequency-domain representations to estimate the s…
HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection
Ke Chen, Xingjian Du, Bilei Zhu +3
Audio classification is an important task of mapping audio samples into their corresponding labels. Recently, the transformer model with self-attention mechanisms has been adopted…