Alert button
Picture for Ramon Prieto

Ramon Prieto

Alert button

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

Oct 01, 2019
Kyu J. Han, Ramon Prieto, Kaixing Wu, Tao Ma

Figure 1 for State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutions
Figure 2 for State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutions
Figure 3 for State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutions
Figure 4 for State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutions
Viaarxiv icon

Attention-based sequence-to-sequence model for speech recognition: development of state-of-the-art system on LibriSpeech and its application to non-native English

Nov 05, 2018
Yan Yin, Ramon Prieto, Bin Wang, Jianwei Zhou, Yiwei Gu, Yang Liu, Hui Lin

Figure 1 for Attention-based sequence-to-sequence model for speech recognition: development of state-of-the-art system on LibriSpeech and its application to non-native English
Figure 2 for Attention-based sequence-to-sequence model for speech recognition: development of state-of-the-art system on LibriSpeech and its application to non-native English
Figure 3 for Attention-based sequence-to-sequence model for speech recognition: development of state-of-the-art system on LibriSpeech and its application to non-native English
Viaarxiv icon