10.9k citations
- University of MichiganUS43 papers
- Massachusetts Institute of TechnologyUS42 papers
- University of Illinois Urbana-ChampaignUS42 papers
- Joint Institute for Nuclear ResearchRU41 papers
- University of PennsylvaniaUS41 papers
- Michigan State UniversityUS40 papers
- University of New MexicoUS40 papers
- University of TsukubaJP40 papers
- University of Wisconsin–MadisonUS40 papers
- Waseda UniversityJP40 papers
- Institute of Physics, Academia SinicaTW39 papers
- National and Kapodistrian University of AthensGR39 papers
12 papers · 1 filter
Actions Speak Louder than Listening: Evaluating Music Style Transfer based on Editing Experience
Wei-Tsung Lu, Meng-Hsuan Wu, Yuh-Ming Chiu +1
The subjective evaluation of music generation techniques has been mostly done with questionnaire-based listening tests while ignoring the perspectives from music composition, arran…
SurpriseNet: Melody Harmonization Conditioning on User-controlled Surprise Contours
Yi-Wei Chen, Hung-Shin Lee, Yen-Hsing Chen +1
The surprisingness of a song is an essential and seemingly subjective factor in determining whether the listener likes it. With the help of information theory, it can be described…
ReconVAT: A Semi-Supervised Automatic Music Transcription Framework for Low-Resource Real-World Data
Kin Wai Cheuk, Dorien Herremans, Li Su
Most of the current supervised automatic music transcription (AMT) models lack the ability to generalize. This means that they have trouble transcribing real-world music recordings…
Drum-Aware Ensemble Architecture for Improved Joint Musical Beat and Downbeat Tracking
Ching-Yu Chiu, Alvin Wen-Yu Su, Yi-Hsuan Yang
This paper presents a novel system architecture that integrates blind source separation with joint beat and downbeat tracking in musical audio signals. The source separation module…
Speech Recognition by Simply Fine-tuning BERT
Wen-Chin Huang, Chia-Hua Wu, Shang-Bao Luo +3
We propose a simple method for automatic speech recognition (ASR) by fine-tuning BERT, which is a language model (LM) trained on large-scale unlabeled text data and can generate ri…
Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs
Wen-Yi Hsiao, Jen-Yu Liu, Yin-Cheng Yeh +1
To apply neural sequence models such as the Transformers to music generation tasks, one has to represent a piece of music by a sequence of tokens drawn from a finite set of pre-def…