These last months have been very intense for us – and, as a result, three papers were recently uploaded to arXiv. Two of those have been accepted for presentation in ISMIR, and are the result of a collaboration with Rong – who is an amazing PhD student (also advised by Xavier) working on Jingju music:
- Score-informed syllable segmentation for a cappella singing voice with convolutional neural networks [code]
- Audio to score matching by combining phonetic and duration information [code]
The third paper was done in collaboration with Dario (an excellent master student!) who was interested in using deep learning models operating directly on the audio: