Blockwise self-attentional encoder models have recently emerged as one
p...
Automatic speech recognition (ASR) based on transducers is widely used. ...
There has been an increased interest in the integration of pretrained sp...
Self-supervised learning (SSL) of speech has shown impressive results in...
We investigate the emergent abilities of the recently proposed web-scale...
Conformer, a convolution-augmented Transformer variant, has become the d...
Recently there have been efforts to introduce new benchmark tasks for sp...
This paper describes our system for the low-resource domain adaptation t...
Most human interactions occur in the form of spoken conversations where ...
ESPnet-ST-v2 is a revamp of the open-source ESPnet-ST toolkit necessitat...
Multilingual Automatic Speech Recognition (ASR) models have extended the...
The network architecture of end-to-end (E2E) automatic speech recognitio...
The black-box nature of end-to-end speech translation (E2E ST) systems m...
In this work, we seek to build effective code-switched (CS) automatic sp...
Self-supervised learning (SSL) models reshaped our approach to speech,
l...
This paper presents BERT-CTC, a novel formulation of end-to-end speech
r...
End-to-end spoken language understanding (SLU) systems are gaining popul...
Sequence-to-Sequence (seq2seq) tasks transcribe the input sequence to a
...
Connectionist Temporal Classification (CTC) is a widely used approach fo...
This paper presents recent progress on integrating speech separation and...
End-to-end (E2E) models are becoming increasingly popular for spoken lan...
Self-Supervised Learning (SSL) models have been successfully applied in
...
Conversational bilingual speech encompasses three types of utterances: t...
As Automatic Speech Processing (ASR) systems are getting better, there i...
The multi-decoder (MD) end-to-end speech translation model has demonstra...
Building language-universal speech recognition systems entails producing...
This paper describes the ESPnet-ST group's IWSLT 2021 submission in the
...
End-to-end approaches for sequence tasks are becoming increasingly popul...