A big convergence of model architectures across language, vision, speech, and multimodal
is emerging. However, under the same name" Transformers", the above areas use different …

A big convergence of model architectures across language, vision, speech, and multimodal
is emerging. However, under the same name” Transformers”, the above areas use different …

This paper presents BERT-CTC, a novel formulation of end-to-end speech recognition that
adapts BERT for connectionist temporal classification (CTC). Our formulation relaxes the …

Streaming Automatic Speech Recognition (ASR) has gained significant attention across
various application scenarios, including video conferencing, live sports events, and …

Automatic speech recognition of a target speaker in the presence of interfering speakers
remains a challenging issue. One approach to tackle this problem is target-speaker speech …

We present BERT-CTC-Transducer (BECTRA), a novel end-to-end automatic speech
recognition (E2E-ASR) model formulated by the transducer with a BERT-enhanced encoder …

RNN-Transducer has been one of promising architectures for end-to-end automatic speech
recognition. Although RNN-Transducer has many advantages including its strong accuracy …

Although end-to-end (E2E) trainable automatic speech recognition (ASR) has shown great
success by jointly learning acoustic and linguistic information, it still suffers from the effect of …

Real-time applications of Automatic Speech Recognition (ASR) on user devices on the edge
require streaming processing. Conformer model has achieved state-of-the-art performance …

Transformer-based models have achieved state-of-the-art performance in various areas of
machine learning, including automatic speech recognition. However, their cost in terms of …