Related papers: Self-Taught Recognizer: Toward Unsupervised Adapta…
Automatic Speech Recognition (ASR) systems, despite large multilingual training, struggle in low-resource scenarios where labeled data is scarce. We propose BEARD (BEST-RQ Encoder Adaptation with Re-training and Distillation), a novel…
Over the last few years, deep learning has grown in popularity for speaker verification, identification, and diarization. Inarguably, a significant part of this success is due to the demonstrated effectiveness of their speaker…
We introduce STAR (Stream Transduction with Anchor Representations), a novel Transformer-based model designed for efficient sequence-to-sequence transduction over streams. STAR dynamically segments input streams to create compressed anchor…
For deep learning-based speech enhancement (SE) systems, the training-test acoustic mismatch can cause notable performance degradation. To address the mismatch issue, numerous noise adaptation strategies have been derived. In this paper, we…
Recent breakthroughs in singing voice synthesis (SVS) have heightened the demand for high-quality annotated datasets, yet manual annotation remains prohibitively labor-intensive and resource-intensive. Existing automatic singing annotation…
This work presents STAR, the first end-to-end speech-to-audio generation framework, designed to enhance efficiency and address error propagation inherent in cascaded systems. Unlike prior approaches relying on text or vision, STAR leverages…
Unsupervised domain adaptation aims to address the problem of classifying unlabeled samples from the target domain whilst labeled samples are only available from the source domain and the data distributions are different in these two…
Recent advancements in deep learning-based wearable human action recognition (wHAR) have improved the capture and classification of complex motions, but adoption remains limited due to the lack of expert annotations and domain discrepancies…
Self-supervised learning (SSL) in the pretraining stage using un-annotated speech data has been successful in low-resource automatic speech recognition (ASR) tasks. However, models trained through SSL are biased to the pretraining data…
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…
Despite rapid progress in the recent past, current speech recognition systems still require labeled training data which limits this technology to a small fraction of the languages spoken around the globe. This paper describes wav2vec-U,…
Scene text recognition (STR) attracts much attention over the years because of its wide application. Most methods train STR model in a fully supervised manner which requires large amounts of labeled data. Although synthetic data contributes…
Speech recognition systems often struggle with data domains that have not been included in the training. To address this, unsupervised domain adaptation has been explored with ensemble and multi-stage teacher-student training methods…
Transfer learning from high-resource languages is known to be an efficient way to improve end-to-end automatic speech recognition (ASR) for low-resource languages. Pre-trained or jointly trained encoder-decoder models, however, do not share…
Active learning is an iterative labeling process that is used to obtain a small labeled subset, despite the absence of labeled data, thereby enabling to train a model for supervised tasks such as text classification. While active learning…
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…
Semi-supervised learning (SSL) is a popular setting aiming to effectively utilize unlabelled data to improve model performance in downstream natural language processing (NLP) tasks. Currently, there are two popular approaches to make use of…
We consider the problem of unsupervised domain adaptation for image classification. To learn target-domain-aware features from the unlabeled data, we create a self-supervised pretext task by augmenting the unlabeled data with a certain type…
Unsupervised domain adaptation (UDA) assumes that source and target domain data are freely available and usually trained together to reduce the domain gap. However, considering the data privacy and the inefficiency of data transmission, it…
Unsupervised domain adaptation (DA) has gained substantial interest in semantic segmentation. However, almost all prior arts assume concurrent access to both labeled source and unlabeled target, making them unsuitable for scenarios…