-
A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation
Non-autoregressive (NAR) models simultaneously generate multiple outputs...
10/11/2021 ∙ by Yosuke Higuchi, et al. ∙
0
∙
share
read it
-
Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy
Pseudo-labeling (PL), a semi-supervised learning (SSL) method where a se...
10/11/2021 ∙ by Yosuke Higuchi, et al. ∙
0
∙
share
read it
-
Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units
In end-to-end automatic speech recognition (ASR), a model is expected to...
10/08/2021 ∙ by Yosuke Higuchi, et al. ∙
0
∙
share
read it
-
Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoring
This article describes an efficient end-to-end speech translation (E2E-S...
09/09/2021 ∙ by Hirofumi Inaguma, et al. ∙
0
∙
share
read it
-
Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition
Pseudo-labeling (PL) has been shown to be effective in semi-supervised a...
06/16/2021 ∙ by Yosuke Higuchi, et al. ∙
0
∙
share
read it
-
The 2020 ESPnet update: new features, broadened applications, performance improvements, and future plans
This paper describes the recent development of ESPnet (https://github.co...
12/23/2020 ∙ by Shinji Watanabe, et al. ∙
0
∙
share
read it
-
Recent Developments on ESPnet Toolkit Boosted by Conformer
In this study, we present recent developments on ESPnet: End-to-End Spee...
10/26/2020 ∙ by Pengcheng Guo, et al. ∙
0
∙
share
read it
-
Improved Mask-CTC for Non-Autoregressive End-to-End ASR
For real-world deployment of automatic speech recognition (ASR), the sys...
10/26/2020 ∙ by Yosuke Higuchi, et al. ∙
0
∙
share
read it
-
Orthros: Non-autoregressive End-to-end Speech Translation with Dual-decoder
Fast inference speed is an important goal towards real-world deployment ...
10/25/2020 ∙ by Hirofumi Inaguma, et al. ∙
0
∙
share
read it
-
Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict
We present Mask CTC, a novel non-autoregressive end-to-end automatic spe...
05/18/2020 ∙ by Yosuke Higuchi, et al. ∙
0
∙
share
read it
