6 papers · 1 filter
Ghost in the Encoder: Decodable Artist Identity Representations in Lyrics-to-Song Generation
Arhan Vohra, Choenden Kyirong, Laura Ibáñez-Martínez +1
Text-to-song generation models can be prompted to imitate specific artists or regurgitate entire songs from their training data. Although these phenomena have been documented behav…
MambaVoice: Lightweight Audiovisual Singing Voice Separation Via A Hybrid Mamba-Transformer Model
Adithi Shankar, Gopika Krishnan, Gloria Haro +2
Isolating a target singing voice from a music video remains challenging, particularly in the presence of multiple vocalists and dense instrumental accompaniment. We propose MambaVo…
MusGU+: Toward a Musician-Centered Evaluation Framework and Discovery Tool for Generative Music AI
Laura Ibáñez-Martínez, Roser Batlle-Roca, Xavier Serra +1
Generative music systems are increasingly presented as tools that democratize music creation, yet their practical suitability for musicians remains underexplored. Prior work includ…
Evaluating Disentangled Representations for Controllable Music Generation
Laura Ibáñez-Martínez, Chukwuemeka Nkama, Andrea Poltronieri +2
Recent approaches in music generation rely on disentangled representations, often labeled as structure and timbre or local and global, to enable controllable synthesis. Yet the und…
From Discord to Harmony: Decomposed Consonance-based Training for Improved Audio Chord Estimation
Andrea Poltronieri, Xavier Serra, Martín Rocamora
Audio Chord Estimation (ACE) holds a pivotal role in music information research, having garnered attention for over two decades due to its relevance for music transcription and ana…
MusGO: A Community-Driven Framework For Assessing Openness in Music-Generative AI
Roser Batlle-Roca, Laura Ibáñez-Martínez, Xavier Serra +2
Since 2023, generative AI has rapidly advanced in the music domain. Despite significant technological advancements, music-generative models raise critical ethical challenges, inclu…