Separating the signals from the mixture when the signals share same frequency and time
domain pattern is always a matter of concern. In natural environment, sound events often …

Emulating the human ability to solve the cocktail party problem, ie, focus on a source of
interest in a complex acoustic scene, is a long standing goal of audio source separation …

Music source separation research has made great advances in recent years, especially
towards the problem of separating vocals, drums, and bass stems from mastered songs. The …

We construct a corpus of Japanese a cappella vocal ensembles (ja-Cappella corpus) for
vocal ensemble separation and synthesis. It consists of 35 copyright-cleared vocal …

Multimodal large models, leveraging extensive datasets and parameters, have provided
superior solutions for multimodal tasks and have been widely applied across various …

We propose a singing voice synthesis (SVS) method for a more unified ensemble singing
voice by modeling interactions between singers. Most existing SVS methods aim to …

In this work, we tackle the challenging problem of separating mono-phonic instrument
mixtures found in chamber music from monaural recordings. This task differs from the Music …

While manual transcription tools exist, music enthusiasts, including amateur singers, still
encounter challenges when transcribing performances into sheet music. This paper …

Music source separation is the task of separating musical sources from an audio mixture. It
has various direct applications including automatic karaoke generation, enhancing musical …