research
∙
09/19/2023
Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model in End-to-End Speech Recognition
We present a novel integration of an instruction-tuned large language mo...
share
research
∙
09/09/2023
Mask-CTC-based Encoder Pre-training for Streaming End-to-End Speech Recognition
Achieving high accuracy with low latency has always been a challenge in ...
research
∙
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...
research
∙
11/02/2022
InterMPL: Momentum Pseudo-Labeling with Intermediate CTC Loss
This paper presents InterMPL, a semi-supervised learning method of end-t...
research
∙
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...
research
∙
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...
research
∙
10/11/2022
CTC Alignments Improve Autoregressive Translation
Connectionist Temporal Classification (CTC) is a widely used approach fo...
research
∙
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...
research
∙
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...
research
∙
10/11/2021
A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation
Non-autoregressive (NAR) models simultaneously generate multiple outputs...
research
∙
10/11/2021
Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy
Pseudo-labeling (PL), a semi-supervised learning (SSL) method where a se...
research
∙
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...
research
∙
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...
research
∙
06/16/2021
Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition
Pseudo-labeling (PL) has been shown to be effective in semi-supervised a...
research
∙
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...
research
∙
10/26/2020
Recent Developments on ESPnet Toolkit Boosted by Conformer
In this study, we present recent developments on ESPnet: End-to-End Spee...
research
∙
10/26/2020
Improved Mask-CTC for Non-Autoregressive End-to-End ASR
For real-world deployment of automatic speech recognition (ASR), the sys...
research
∙
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 ...
research
∙
05/18/2020