293 citations · 1k across the 72 of their papers we have counts for
7 papers · 1 filter
JukeDrummer: Conditional Beat-aware Audio-domain Drum Accompaniment Generation via Transformer VQ-VAE
Yueh-Kao Wu, Ching-Yu Chiu, Yi-Hsuan Yang
This paper proposes a model that generates a drum track in the audio domain to play along to a user-provided drum-free recording. Specifically, using paired data of drumless tracks…
An Analysis Method for Metric-Level Switching in Beat Tracking
Ching-Yu Chiu, Meinard Müller, Matthew E. P. Davies +2
For expressive music, the tempo may change over time, posing challenges to tracking the beats by an automatic model. The model may first tap to the correct tempo, but then may fail…
Single-Use Delegatable Signatures Based on Smart Contracts
Stephan Krenn, Thomas Lorünser
Delegation of cryptographic signing rights has found many application in the literature and the real world. However, despite very advanced functionalities and specific use cases, e…
Exploiting Pre-trained Feature Networks for Generative Adversarial Networks in Audio-domain Loop Generation
Yen-Tung Yeh, Bo-Yu Chen, Yi-Hsuan Yang
While generative adversarial networks (GANs) have been widely used in research on audio generation, the training of a GAN model is known to be unstable, time consuming, and data in…
Compose & Embellish: Well-Structured Piano Performance Generation via A Two-Stage Approach
Shih-Lun Wu, Yi-Hsuan Yang
Even with strong sequence models like Transformers, generating expressive piano performances with long-range musical structures remains challenging. Meanwhile, methods to compose w…
DDSP-based Singing Vocoders: A New Subtractive-based Synthesizer and A Comprehensive Evaluation
Da-Yi Wu, Wen-Yi Hsiao, Fu-Rong Yang +5
A vocoder is a conditional audio generation model that converts acoustic features such as mel-spectrograms into waveforms. Taking inspiration from Differentiable Digital Signal Pro…
towards automatic transcription of polyphonic electric guitar music:a new dataset and a multi-loss transformer model
Yu-Hua Chen, Wen-Yi Hsiao, Tsu-Kuang Hsieh +2
In this paper, we propose a new dataset named EGDB, that con-tains transcriptions of the electric guitar performance of 240 tab-latures rendered with different tones. Moreover, we…