Yosuke Higuchi | DeepAI

DeepAI

Featured Co-authors

Graham Neubig
222 publications
Shinji Watanabe
198 publications
Alan W Black
72 publications
Florian Metze
72 publications
Jonathan Le Roux
55 publications
Yifan Peng
47 publications
Kevin Duh
44 publications
Takaaki Hori
37 publications
Tomoki Hayashi
37 publications
Wen-Chin Huang
35 publications
Hirofumi Inaguma
31 publications

∙ 11/10/2022

A Study on the Integration of Pre-trained SSL, ASR, LM and SLU Models for Spoken Language Understanding

Collecting sufficient labeled data for spoken language understanding (SL...

Yifan Peng, et al. ∙

∙ 11/02/2022

InterMPL: Momentum Pseudo-Labeling with Intermediate CTC Loss

This paper presents InterMPL, a semi-supervised learning method of end-t...

Yosuke Higuchi, et al. ∙

∙ 11/02/2022

BECTRA: Transducer-based End-to-End ASR with BERT-Enhanced Encoder

We present BERT-CTC-Transducer (BECTRA), a novel end-to-end automatic sp...

Yosuke Higuchi, et al. ∙

∙ 10/29/2022

BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model

This paper presents BERT-CTC, a novel formulation of end-to-end speech r...

Yosuke Higuchi, et al. ∙

∙ 10/11/2022

CTC Alignments Improve Autoregressive Translation

Connectionist Temporal Classification (CTC) is a widely used approach fo...

Brian Yan, et al. ∙

∙ 01/25/2022

Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models

While Transformers have achieved promising results in end-to-end (E2E) a...

Keqi Deng, et al. ∙

∙ 10/20/2021

An Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASR

In the present paper, an attempt is made to combine Mask-CTC and the tri...

Huaibo Zhao, et al. ∙

∙ 10/11/2021

A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation

Non-autoregressive (NAR) models simultaneously generate multiple outputs...

Yosuke Higuchi, et al. ∙

∙ 10/11/2021

Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy

Pseudo-labeling (PL), a semi-supervised learning (SSL) method where a se...

Yosuke Higuchi, et al. ∙

∙ 10/08/2021

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...

Yosuke Higuchi, et al. ∙

∙ 09/09/2021

Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoring

This article describes an efficient end-to-end speech translation (E2E-S...

Hirofumi Inaguma, et al. ∙

∙ 06/16/2021

Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition

Pseudo-labeling (PL) has been shown to be effective in semi-supervised a...

Yosuke Higuchi, et al. ∙

∙ 12/23/2020

The 2020 ESPnet update: new features, broadened applications, performance improvements, and future plans

This paper describes the recent development of ESPnet (https://github.co...

Shinji Watanabe, et al. ∙

∙ 10/26/2020

Recent Developments on ESPnet Toolkit Boosted by Conformer

In this study, we present recent developments on ESPnet: End-to-End Spee...

Pengcheng Guo, et al. ∙

∙ 10/26/2020

Improved Mask-CTC for Non-Autoregressive End-to-End ASR

For real-world deployment of automatic speech recognition (ASR), the sys...

Yosuke Higuchi, et al. ∙

∙ 10/25/2020

Orthros: Non-autoregressive End-to-end Speech Translation with Dual-decoder

Fast inference speed is an important goal towards real-world deployment ...

Hirofumi Inaguma, et al. ∙

∙ 05/18/2020

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...

Yosuke Higuchi, et al. ∙