A Comparative Study on Transformer vs RNN in Speech Applications

Sequence-to-sequence models have been widely used in end-to-end speech processing, for example, automatic speech recognition (ASR), speech translation (ST), and text-to-speech (TTS). This paper focuses on an emergent sequence-to-sequence model called Transformer, which achieves state-of-the-art perf...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2019-09
Hauptverfasser:	Karita, Shigeki, Chen, Nanxin, Hayashi, Tomoki, Hori, Takaaki, Inaguma, Hirofumi, Jiang, Ziyan, Someki, Masao, Nelson Enrique Yalta Soplin, Yamamoto, Ryuichi, Wang, Xiaofei, Watanabe, Shinji, Yoshimura, Takenori, Zhang, Wangyou
Format:	Artikel
Sprache:	eng
Schlagworte:	Automatic speech recognition Benchmarks Comparative studies Computer Science - Computation and Language Computer Science - Sound Machine translation Natural language processing Recurrent neural networks Speech processing Transformers Voice recognition
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!