Conference Papers

1. Jiawen Huang, Felipe Sousa, Emir Demirel, Emmanouil Benetos, Igor Gadelha. “Enhancing Lyrics Transcription on Music Mixtures with Consistency Loss”, In 26th Annual Conference of the International Speech Communication Association, Interspeech 2025, Rotterdam, The Netherlands, August 17-21, 2025. [Github]
2. Jiawen Huang, Emmanouil Benetos. “Towards Building an End-to-End Multilingual Automatic Lyrics Transcription Model”, 32th European Signal Processing Conference, Lyon, France, 2024 [Github]
3. (9th author) Ruibin Yuan, Yinghao Ma, et al. “MARBLE: Music Audio Representation Benchmark for Universal Evaluation”, NeurIPS Datasets and Benchmarks 2023, New Orleans, United States, 2023.
4. Jiawen Huang, Emmanouil Benetos, Sebastian Ewert. “Improving Lyrics Alignment through Joint Pitch Detection”, 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, 2022. [Github]
5. Jiawen Huang, Ju-Chiang Wang, Jordan B. L. Smith, Xuchen Song, Yuxuan Wang. “Modeling the Compatibility of Stem Tracks to Generate Music Mashups”, 35th AAAI Conference on Artificial Intelligence, Vancouver, Canada, 2021.
6. Jiawen Huang, Yun-Ning Hung, Ashis Pati, Siddharth Kumar Gururani, Alexander Lerch. “Score-informed Networks for Music Performance Assessment”, 21st International Society for Music Information Retrieval Conference, Montréal, Canada, 2020. [Github]
7. Jiawen Huang, Alexander Lerch. “Automatic Assessment of Sight-reading Exercises”, 20th International Society for Music Information Retrieval Conference, Delft, The Netherlands, 2019. [Github]

Journal Papers

1. Jiawen Huang, Emmanouil Benetos. “Singing to Speech Conversion with Generative Flow”. EURASIP Journal on Audio Speech and Music Processing, 2025(1):12, 2025. [Github]
2. (Under Review)
3. (Under Review)

Extended Abstract

1. Jiawen Huang, Emmanouil Benetos. “Evaluating Lyrics Alignment under Source Separated Conditions”. Late-breaking Demo, 25th International Society for Music Information Retrieval Conference, Daejeon, Korea, 2025. [Github]
2. Jiawen Huang, Emmanouil Benetos. “Multilingual Integration in Lyrics Transcription: Data, Language Conditioning, and Transliteration Augmentation”. UK and Ireland Speech Workshop 2024. [Github]
3. Jiawen Huang, Emmanouil Benetos. “Singing to Speech Conversion with Generative Flow”. Sheffield Speech Synthesis Workshop 2023.

Other Links

1. Data preparation pipeline for lyrics transcription and alignment [Github]
2. LyricWhiz (the initial release of the MulJam dataset) [Github]