Device-Guided Music Transfer
By: Manh Pham Hung , Changshuo Hu , Ting Dang and more
Potential Business Impact:
Makes music sound good on any speaker.
Device-guided music transfer adapts playback across unseen devices for users who lack them. Existing methods mainly focus on modifying the timbre, rhythm, harmony, or instrumentation to mimic genres or artists, overlooking the diverse hardware properties of the playback device (i.e., speaker). Therefore, we propose DeMT, which processes a speaker's frequency response curve as a line graph using a vision-language model to extract device embeddings. These embeddings then condition a hybrid transformer via feature-wise linear modulation. Fine-tuned on a self-collected dataset, DeMT enables effective speaker-style transfer and robust few-shot adaptation for unseen devices, supporting applications like device-style augmentation and quality enhancement.
Similar Papers
Sound and Music Biases in Deep Music Transcription Models: A Systematic Analysis
Sound
Helps computers understand music better, not just piano.
Controllable Embedding Transformation for Mood-Guided Music Retrieval
Sound
Changes song mood without changing its style.
Let the Model Learn to Feel: Mode-Guided Tonality Injection for Symbolic Music Emotion Recognition
Sound
Helps computers understand music's feelings better.