arXiv Open Access 2017

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

Dan Lim

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.CL

Penulis (1)

Dan Lim

Format Sitasi

APA MLA BibTeX

Lim, D. (2017). Convolutional Attention-based Seq2Seq Neural Network for End-to-End ASR. https://arxiv.org/abs/1710.04515

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2017
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓