Related papers: Conformer-1: Robust ASR via Large-Scale Semisuperv…

Recently, self-supervised learning (SSL) from unlabelled speech data has gained increased attention in the automatic speech recognition (ASR) community. Typical SSL methods include autoregressive predictive coding (APC), Wav2vec2.0, and…

We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge base. The biggest…

Recently, a semi-supervised learning method known as "noisy student training" has been shown to improve image classification performance of deep networks significantly. Noisy student training is an iterative self-training method that…

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

Speech representations learned in a self-supervised fashion from massive unlabeled speech corpora have been adapted successfully toward several downstream tasks. However, such representations may be skewed toward canonical data…

Self-supervised learning (SSL) to learn high-level speech representations has been a popular approach to building Automatic Speech Recognition (ASR) systems in low-resource settings. However, the common assumption made in literature is that…

Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…

End-to-end models for robust automatic speech recognition (ASR) have not been sufficiently well-explored in prior work. With end-to-end models, one could choose to preprocess the input speech using speech enhancement techniques and train…

We study the problem of word-level confidence estimation in subword-based end-to-end (E2E) models for automatic speech recognition (ASR). Although prior works have proposed training auxiliary confidence models for ASR systems, they do not…

Building competitive automatic speech recognition (ASR) models usually requires large-scale au- dio supervision, which makes reproduction and specialization expensive. We study Ark-ASR, a 0.6B- parameter audio-conditioned language model…

Large scale machine learning (ML) systems such as the Alexa automatic speech recognition (ASR) system continue to improve with increasing amounts of manually transcribed training data. Instead of scaling manual transcription to impractical…

Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech Recognition (ASR) performance in low-resource settings. In this context, it has been demonstrated that larger self-supervised feature extractors are crucial…

Noise robustness is essential for deploying automatic speech recognition (ASR) systems in real-world environments. One way to reduce the effect of noise interference is to employ a preprocessing module that conducts speech enhancement, and…

Conformers have recently been proposed as a promising modelling approach for automatic speech recognition (ASR), outperforming recurrent neural network-based approaches and transformers. Nevertheless, in general, the performance of these…

Whisper is a recent Automatic Speech Recognition (ASR) model displaying impressive robustness to both out-of-distribution inputs and random noise. In this work, we show that this robustness does not carry over to adversarial noise. We show…

Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language…

Pseudo-labeling (PL) has been shown to be effective in semi-supervised automatic speech recognition (ASR), where a base model is self-trained with pseudo-labels generated from unlabeled data. While PL can be further improved by iteratively…

In this paper, we propose a three-stage training methodology to improve the speech recognition accuracy of low-resource languages. We explore and propose an effective combination of techniques such as transfer learning, encoder freezing,…

This paper presents a novel optimization framework for automatic speech recognition (ASR) with the aim of reducing hallucinations produced by an ASR model. The proposed framework optimizes the ASR model to maximize an expected factual…

The interest in employing automatic speech recognition (ASR) in applications for reading practice has been growing in recent years. In a previous study, we presented an ASR-based Dutch reading tutor application that was developed to provide…