Automatic Lyrics Transcription using Dilated Convolutional Neural Networks with Self-Attention

TL;DR

This paper introduces a novel automatic lyrics transcription system using dilated convolutional neural networks with self-attention, achieving state-of-the-art results on English karaoke data.

Contribution

It presents a complete pipeline for ALT with a new neural network architecture and analysis of self-attention mechanisms, setting a new baseline.

Findings

Achieved significant improvement over previous ALT systems.

Analyzed the impact of self-attention parameters on performance.

Provided a robust model for English lyrics transcription.

Abstract

Speech recognition is a well developed research field so that the current state of the art systems are being used in many applications in the software industry, yet as by today, there still does not exist such robust system for the recognition of words and sentences from singing voice. This paper proposes a complete pipeline for this task which may commonly be referred as automatic lyrics transcription (ALT). We have trained convolutional time-delay neural networks with self-attention on monophonic karaoke recordings using a sequence classification objective for building the acoustic model. The dataset used in this study, DAMP - Sing! 300x30x2 [1] is filtered to have songs with only English lyrics. Different language models are tested including MaxEnt and Recurrent Neural Networks based methods which are trained on the lyrics of pop songs in English. An in-depth analysis of the self-attention mechanism is held while tuning its context width and the number of attention heads. Using the best settings, our system achieves notable improvement to the state-of-the-art in ALT and provides a new baseline for the task.