End-to-end Lyrics Alignment for Polyphonic Music Using an Audio-to-Character Recognition Model

TL;DR

This paper introduces an end-to-end audio-to-character recognition system for lyrics alignment in polyphonic music, achieving high accuracy without complex sub-modules or fine-grained annotations.

Contribution

A novel Wave-U-Net based model that directly predicts character probabilities from raw audio, simplifying the process and working with weak annotations.

Findings

Achieves a mean alignment error of 0.35s on a standard dataset.

Outperforms state-of-the-art methods by an order of magnitude.

Operates without sub-modules like vocal separation or detection.

Abstract

Time-aligned lyrics can enrich the music listening experience by enabling karaoke, text-based song retrieval and intra-song navigation, and other applications. Compared to text-to-speech alignment, lyrics alignment remains highly challenging, despite many attempts to combine numerous sub-modules including vocal separation and detection in an effort to break down the problem. Furthermore, training required fine-grained annotations to be available in some form. Here, we present a novel system based on a modified Wave-U-Net architecture, which predicts character probabilities directly from raw audio using learnt multi-scale representations of the various signal components. There are no sub-modules whose interdependencies need to be optimized. Our training procedure is designed to work with weak, line-level annotations available in the real world. With a mean alignment error of 0.35s on a standard dataset our system outperforms the state-of-the-art by an order of magnitude.