Related papers: Self-Attention Networks for Connectionist Temporal…

This paper presents a novel algorithm for building an automatic speech recognition (ASR) model with imperfect training data. Imperfectly transcribed speech is a prevalent issue in human-annotated speech corpora, which degrades the…

Training the state-of-the-art speech-to-text (STT) models in mobile devices is challenging due to its limited resources relative to a server environment. In addition, these models are trained on generic datasets that are not exhaustive in…

We present a novel approach to end-to-end automatic speech recognition (ASR) that utilizes pre-trained masked language models (LMs) to facilitate the extraction of linguistic information. The proposed models, BERT-CTC and BECTRA, are…

Self-attention has been a huge success for many downstream tasks in NLP, which led to exploration of applying self-attention to speech problems as well. The efficacy of self-attention in speech applications, however, seems not fully blown…

Previous work has shown that neural encoder-decoder speech recognition can be improved with hierarchical multitask learning, where auxiliary tasks are added at intermediate layers of a deep encoder. We explore the effect of hierarchical…

Although self-attention networks (SANs) have advanced the state-of-the-art on various NLP tasks, one criticism of SANs is their ability of encoding positions of input words (Shaw et al., 2018). In this work, we propose to augment SANs with…

In this paper, we study the problem of text line recognition. Unlike most approaches targeting specific domains such as scene-text or handwritten documents, we investigate the general problem of developing a universal architecture that can…

End-To-End speech recognition have become increasingly popular in mandarin speech recognition and achieved delightful performance. Mandarin is a tonal language which is different from English and requires special treatment for the acoustic…

End-to-end (E2E) automatic speech recognition (ASR) systems have revolutionized the field by integrating all components into a single neural network, with attention-based encoder-decoder models achieving state-of-the-art performance.…

Semi-supervised learning (SSL) is an active area of research which aims to utilize unlabelled data in order to improve the accuracy of speech recognition systems. The current study proposes a methodology for integration of two key ideas: 1)…

End-to-end automatic speech recognition directly maps input speech to characters. However, the mapping can be problematic when several different pronunciations should be mapped into one character or when one pronunciation is shared among…

Multilingual models for Automatic Speech Recognition (ASR) are attractive as they have been shown to benefit from more training data, and better lend themselves to adaptation to under-resourced languages. However, initialisation from…

Self-attention (SA) based models have recently achieved significant performance improvements in hybrid and end-to-end automatic speech recognition (ASR) systems owing to their flexible context modeling capability. However, it is also known…

Due to the modality discrepancy between textual and acoustic modeling, efficiently transferring linguistic knowledge from a pretrained language model (PLM) to acoustic encoding for automatic speech recognition (ASR) still remains a…

This review paper provides a comprehensive analysis of recent advances in automatic speech recognition (ASR) with bidirectional encoder representations from transformers BERT and connectionist temporal classification (CTC) transformers. The…

This paper advances the design of CTC-based all-neural (or end-to-end) speech recognizers. We propose a novel symbol inventory, and a novel iterated-CTC method in which a second system is used to transform a noisy initial output into a…

Connectionist Temporal Classification (CTC) based end-to-end speech recognition system usually need to incorporate an external language model by using WFST-based decoding in order to achieve promising results. This is more essential to…

Speech is one of the most effective ways of communication among humans. Even though audio is the most common way of transmitting speech, very important information can be found in other modalities, such as vision. Vision is particularly…

Many machine learning problems such as speech recognition, gesture recognition, and handwriting recognition are concerned with simultaneous segmentation and labeling of sequence data. Latent-dynamic conditional random field (LDCRF) is a…

This paper presents an overview and evaluation of some of the end-to-end ASR models on long-form audios. We study three categories of Automatic Speech Recognition(ASR) models based on their core architecture: (1) convolutional, (2)…