About NUS AutoLyrixAlign
NUS AutoLyrixAlign is a system that automatically provides word-level alignment of a given lyrics text to a given polyphonic music audio file. This system has been developed by the music research group at the HLT lab, NUS: Chitralekha Gupta, Emre Yilmaz, and Haizhou Li.
Please upload an MP3 file or a youtube link of the song and its corresponding lyrics text file. The system typically takes about 2 min to process a 4 min long audio file. You may download the word-aligned output file in json or txt format. The txt format file that can be directly used on open software such as Audacity.
This system has outperformed all other systems in the International Music Information Retrieval Evaluation eXchange platform MIREX 2019, with mean absolute word alignment error of less than 200 ms across all test datasets. (Poster link, MirexResults) This work has been submitted to ICASSP 2020. You may refer to the submitted version here. The github repository of this system is here.
Upload Your Songs
Our Relevant Publications
- 1. C. Gupta, E. Yılmaz, H. Li, "Automatic Lyrics Alignment and Transcription in Polyphonic Music: Does Background Music Help?," arXiv preprint:1909.10200v2 [eess.AS], 2019 (submitted to ICASSP 2020).
- 2. C. Gupta∗, B. Sharma∗, H. Li, and Y. Wang, "Automatic lyrics-to-audio alignment on polyphonic music using singing-adapted acoustic models," in Proc. ICASSP, 2019. (∗equal contributors)
- 3. C. Gupta, E. Yılmaz, and H. Li, "Acoustic modeling for automatic lyrics-to-audio alignment," in Proc. Interspeech, 2019.
- 4. C. Gupta, H. Li, and Y. Wang, "Automatic Pronunciation Evaluation of Singing," in Interspeech, 2018