DeepAI AI Chat
Log In Sign Up

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

by   Emir Demirel, et al.
Queen Mary University of London

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.


SAN-M: Memory Equipped Self-Attention for End-to-End Speech Recognition

End-to-end speech recognition has become popular in recent years, since ...

State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutions

Self-attention has been a huge success for many downstream tasks in NLP,...

Efficient conformer-based speech recognition with linear attention

Recently, conformer-based end-to-end automatic speech recognition, which...

Deep model with built-in self-attention alignment for acoustic echo cancellation

With recent research advances, deep learning models have become an attra...

CNN self-attention voice activity detector

In this work we present a novel single-channel Voice Activity Detector (...

An Overview of Neural Network Compression

Overparameterized networks trained to convergence have shown impressive ...

NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets

In this paper, we present an update to the NISQA speech quality predicti...