Convolutional Attention-based Seq2Seq Neural Network for End-to-End ASR

TL;DR

This paper presents a convolutional attention-based sequence-to-sequence neural network with advanced techniques like batch normalization and residual connections, achieving competitive phoneme error rates for end-to-end automatic speech recognition.

Contribution

It introduces a novel convolutional attention-based seq2seq model incorporating modern neural network algorithms for improved speech recognition performance.

Findings

Achieved 15.8% phoneme error rate on TIMIT dataset

Demonstrated effectiveness of the proposed model for end-to-end ASR

Integrated multiple neural network techniques to enhance accuracy

Abstract

This thesis introduces the sequence to sequence model with Luong's attention mechanism for end-to-end ASR. It also describes various neural network algorithms including Batch normalization, Dropout and Residual network which constitute the convolutional attention-based seq2seq neural network. Finally the proposed model proved its effectiveness for speech recognition achieving 15.8% phoneme error rate on TIMIT dataset.