Showing 2021Show all
3 papers · 1 filter
cs.SD2021
MSTRE-Net: Multistreaming Acoustic Modeling for Automatic Lyrics Transcription
Emir Demirel, Sven Ahlbäck, Simon Dixon
This paper makes several contributions to automatic lyrics transcription (ALT) research. Our main contribution is a novel variant of the Multistreaming Time-Delay Neural Network (M…
cs.IR2021
Computational Pronunciation Analysis in Sung Utterances
Emir Demirel, Sven Ahlback, Simon Dixon
Recent automatic lyrics transcription (ALT) approaches focus on building stronger acoustic models or in-domain language models, while the pronunciation aspect is seldom touched upo…
cs.SD2021
Low Resource Audio-to-Lyrics Alignment From Polyphonic Music Recordings
Emir Demirel, Sven Ahlbäck, Simon Dixon
Lyrics alignment in long music recordings can be memory exhaustive when performed in a single pass. In this study, we present a novel method that performs audio-to-lyrics alignment…