/AutoLyrixAlign

Pre-trained model and script to automatically align lyrics to polyphonic audio

AutoLyrixAlign

Pre-trained model and script to automatically align lyrics to polyphonic audio

Description

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 team from HLT-NUS (Chitralekha Gupta, Emre Yilmaz, Haizhou Li). It has outperformed all other systems in the International Music Information Retrieval Evaluation eXchange platform MIREX 2019. (Poster link, MirexResults)

Cite

If this tool is useful to you, please cite our work: C. Gupta, E. Yılmaz and H. Li, "Automatic Lyrics Alignment and Transcription in Polyphonic Music: Does Background Music Help?," ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2020, pp. 496-500, doi: 10.1109/ICASSP40776.2020.9054567.

arXiv.

Code

Please download the code-base for the best performing pre-trained model and the associated scripts from here. Please follow the Readme file in this folder for further instructions.

License

The code and models in this repository are licensed under the GNU General Public License Version 3. For commercial use of this code and models, separate commercial licensing is also available. Please see the contacts below.

Contact

Chitralekha Gupta at chitralekha[at]nus[dot]edu[dot]sg

Emre Yilmaz at emre[at]nus[dot]edu[dot]sg

Haizhou Li at haizhou[dot]li[at]nus[dot]edu[dot]sg