Related papers: Better Semi-supervised Learning for Multi-domain A…

Fine-tuning pretrained ASR models for specific domains is challenging for small organizations with limited labeled data and computational resources. Here, we explore different data selection pipelines and propose a robust approach that…

Automatic speech recognition (ASR) systems often degrade on accented speech because acoustic-phonetic and prosodic shifts induce a mismatch to training data, making labeled accent adaptation costly. However, common pseudo-label selection…

Self- and semi-supervised learning methods have been actively investigated to reduce labeled training data or enhance the model performance. However, the approach mostly focus on in-domain performance for public datasets. In this study, we…

While deep learning based end-to-end automatic speech recognition (ASR) systems have greatly simplified modeling pipelines, they suffer from the data sparsity issue. In this work, we propose a self-training method with an end-to-end system…

Fine tuning self supervised pretrained models using pseudo labels can effectively improve speech recognition performance. But, low quality pseudo labels can misguide decision boundaries and degrade performance. We propose a simple yet…

Semi-supervised learning in automatic speech recognition (ASR) typically relies on pseudo-labeling, which often suffers from confirmation bias and error accumulation due to noisy supervision. To address this limitation, we propose ReHear, a…

Recent studies have shown that the benefits provided by self-supervised pre-training and self-training (pseudo-labeling) are complementary. Semi-supervised fine-tuning strategies under the pre-training framework, however, remain…

On-device Automatic Speech Recognition (ASR) models trained on speech data of a large population might underperform for individuals unseen during training. This is due to a domain shift between user data and the original training data,…

A novel semi-supervised learning technique is introduced based on a simple iterative learning cycle together with learned thresholding techniques and an ensemble decision support system. State-of-the-art model performance and increased…

This paper presents Conformer-1, an end-to-end Automatic Speech Recognition (ASR) model trained on an extensive dataset of 570k hours of speech audio data, 91% of which was acquired from publicly available sources. To achieve this, we…

Streaming end-to-end speech recognition models have been widely applied to mobile devices and show significant improvement in efficiency. These models are typically trained on the server using transcribed speech data. However, the server…

Recently self-supervised learning has emerged as an effective approach to improve the performance of automatic speech recognition (ASR). Under such a framework, the neural network is usually pre-trained with massive unlabeled data and then…

Semi-supervised learning leverages unlabeled data to enhance model performance, addressing the limitations of fully supervised approaches. Among its strategies, pseudo-supervision has proven highly effective, typically relying on one or…

Semi-supervised learning lately has shown much promise in improving deep learning models when labeled data is scarce. Common among recent approaches is the use of consistency training on a large amount of unlabeled data to constrain model…

Semi-supervised training (SST) is a common approach to leverage untranscribed/unlabeled speech data to improve automatic speech recognition performance in low-resource languages. However, if the available unlabeled speech is mismatched to…

While Automatic Speech Recognition (ASR) models have shown significant advances with the introduction of unsupervised or self-supervised training techniques, these improvements are still only limited to a subsection of languages and…

In recent years, speech-based self-supervised learning (SSL) has made significant progress in various tasks, including automatic speech recognition (ASR). An ASR model with decent performance can be realized by fine-tuning an SSL model with…

Unpaired text and audio injection have emerged as dominant methods for improving ASR performance in the absence of a large labeled corpus. However, little guidance exists on deploying these methods to improve production ASR systems that are…

Recent work has shown that it is possible to train an $\textit{unsupervised}$ automatic speech recognition (ASR) system using only unpaired audio and text. Existing unsupervised ASR methods assume that no labeled data can be used for…

We address the problem of efficient acoustic-model refinement (continuous retraining) using semi-supervised and active learning for a low resource Indian language, wherein the low resource constraints are having i) a small labeled corpus…