相关论文: Reducing Barriers to Self-Supervised Learning: HuB…

Self-supervised learning has been used to leverage unlabelled data, improving accuracy and generalisation of speech systems through the training of representation models. While many recent works have sought to produce effective…

Few-shot keyword spotting aims to detect previously unseen keywords with very limited labeled samples. A pre-training and adaptation paradigm is typically adopted for this task. While effective in clean conditions, most existing approaches…

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…

Neural networks have demonstrated exceptional performance in supervised learning, benefiting from abundant high-quality annotated data. However, obtaining such data in real-world scenarios is costly and labor-intensive. Semi-supervised…

We explore the impact of training with more diverse datasets, characterized by the number of unique samples, on the performance of self-supervised learning (SSL) under a fixed computational budget. Our findings consistently demonstrate that…

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…

While audio-visual speech models can yield superior performance and robustness compared to audio-only models, their development and adoption are hindered by the lack of labeled and unlabeled audio-visual data and the cost to deploy one…

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…

In this study, we aim to explore efficient tuning methods for speech self-supervised learning. Recent studies show that self-supervised learning (SSL) can learn powerful representations for different speech tasks. However, fine-tuning…

Audio-based automatic speech recognition (ASR) degrades significantly in noisy environments and is particularly vulnerable to interfering speech, as the model cannot determine which speaker to transcribe. Audio-visual speech recognition…

Semi-Supervised Learning (SSL) has been proved to be an effective way to leverage both labeled and unlabeled data at the same time. Recent semi-supervised approaches focus on deep neural networks and have achieved promising results on…

Self-supervised speech representation learning has become essential for extracting meaningful features from untranscribed audio. Recent advances highlight the potential of deriving discrete symbols from the features correlated with…

Self-supervised learning (SSL) has significantly advanced acoustic representation learning. However, most existing models are optimised for either speech or audio event understanding, resulting in a persistent gap between these two domains.…

Sustainable artificial intelligence focuses on data, hardware, and algorithms to make machine learning models more environmentally responsible. In particular, machine learning models for speech representations are computationally expensive,…

Recently, fine-tuning large pre-trained Transformer models using downstream datasets has received a rising interest. Despite their success, it is still challenging to disentangle the benefits of large-scale datasets and Transformer…

Self-supervised learning enables the training of large neural models without the need for large, labeled datasets. It has been generating breakthroughs in several fields, including computer vision, natural language processing, biology, and…

Recently, self-supervised learning (SSL) has achieved tremendous success in learning image representation. Despite the empirical success, most self-supervised learning methods are rather "inefficient" learners, typically taking hundreds of…

Pre-training with self-supervised models, such as Hidden-unit BERT (HuBERT) and wav2vec 2.0, has brought significant improvements in automatic speech recognition (ASR). However, these models usually require an expensive computational cost…

Despite their impressive success, training foundation models remains computationally costly. This paper investigates how to efficiently train speech foundation models with self-supervised learning (SSL) under a limited compute budget. We…

Recent advances in self-supervised speech models have shown significant improvement in many downstream tasks. However, these models predominantly centered on frame-level training objectives, which can fall short in spoken language…