相关论文: Neural Model Reprogramming with Similarity Based M…

Low resource automatic speech recognition (ASR) is a useful but thorny task, since deep learning ASR models usually need huge amounts of training data. The existing models mostly established a bottleneck (BN) layer by pre-training on a…

Semi-supervised domain adaptation (SSDA) has been extensively researched due to its ability to improve classification performance and generalization ability of models by using a small amount of labeled data on the target domain. However,…

Semi-supervised learning (SSL) has shown considerable potential in medical image segmentation, primarily leveraging consistency regularization and pseudo-labeling. However, many SSL approaches only pay attention to low-level consistency and…

Building an automatic speech recognition (ASR) system from scratch requires a large amount of annotated speech data, which is difficult to collect in many languages. However, there are cases where the low-resource language shares a common…

Code-switching (CS) refers to the switching of languages within a speech signal and results in language confusion for automatic speech recognition (ASR). To address language confusion, we propose a language alignment loss (LAL) that aligns…

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…

Automatic target recognition (ATR) is an important use case for synthetic aperture radar (SAR) image interpretation. Recent years have seen significant advancements in SAR ATR technology based on semi-supervised learning. However, existing…

Spoken language understanding (SLU) treats automatic speech recognition (ASR) and natural language understanding (NLU) as a unified task and usually suffers from data scarcity. We exploit an ASR and NLU joint training method based on meta…

Self-supervised learning (SSL) leverages large amounts of unlabelled data to learn rich speech representations, fostering improvements in automatic speech recognition (ASR), even when only a small amount of labelled data is available for…

Despite the success of sequence-to-sequence approaches in automatic speech recognition (ASR) systems, the models still suffer from several problems, mainly due to the mismatch between the training and inference conditions. In the…

In this paper, we investigate the use of prediction-adaptation-correction recurrent neural networks (PAC-RNNs) for low-resource speech recognition. A PAC-RNN is comprised of a pair of neural networks in which a {\it correction} network uses…

In the domain of air traffic control (ATC) systems, efforts to train a practical automatic speech recognition (ASR) model always faces the problem of small training samples since the collection and annotation of speech samples are expert-…

Structured prediction tasks, like machine translation, involve learning functions that map structured inputs to structured outputs. Recurrent Neural Networks (RNNs) have historically been a popular choice for such tasks, including in…

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…

With the success of pre-trained visual-language (VL) models such as CLIP in visual representation tasks, transferring pre-trained models to downstream tasks has become a crucial paradigm. Recently, the prompt tuning paradigm, which draws…

End-to-end automatic speech recognition (ASR) systems are increasingly popular due to their relative architectural simplicity and competitive performance. However, even though the average accuracy of these systems may be high, the…

It is an effective way that improves the performance of the existing Automatic Speech Recognition (ASR) systems by retraining with more and more new training data in the target domain. Recently, Deep Neural Network (DNN) has become a…

Automatic speech recognition (ASR) models rely on high-quality transcribed data for effective training. Generating pseudo-labels for large unlabeled audio datasets often relies on complex pipelines that combine multiple ASR outputs through…

Recent advancements in transfer learning have made it a promising approach for domain adaptation via transfer of learned representations. This is especially when relevant when alternate tasks have limited samples of well-defined and labeled…

Most existing masked audio modeling (MAM) methods learn audio representations by masking and reconstructing local spectrogram patches. However, the reconstruction loss mainly accounts for the signal-level quality of the reconstructed…