MSTRE-Net: Multistreaming Acoustic Modeling for Automatic Lyrics Transcription

Understand

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 (MTDNN) architecture, called MSTRE-Net, which processes the temporal information using multiple streams in parallel with varying resolutions keeping the network more compact, and thus with a faster inference and an improved recognition rate than having identical TDNN streams.
• In addition, two novel preprocessing steps prior to training the acoustic model are proposed.
• First, we suggest using recordings from both monophonic and polyphonic domains during training the acoustic model.