Related papers: Phoneme Segmentation Using Self-Supervised Speech …

While models in audio and speech processing are becoming deeper and more end-to-end, they as a consequence need expensive training on large data, and are often brittle. We build on a classical model of human hearing and make it…

Detailed mobile sensing data from phones, watches, and fitness trackers offer an unparalleled opportunity to quantify and act upon previously unmeasurable behavioral changes in order to improve individual health and accelerate responses to…

The recent tremendous success of unsupervised word embeddings in a multitude of applications raises the obvious question if similar methods could be derived to improve embeddings (i.e. semantic representations) of word sequences as well. We…

Self-supervised learning models have revolutionized the field of speech processing. However, the process of fine-tuning these models on downstream tasks requires substantial computational resources, particularly when dealing with multiple…

In the field of semi-supervised medical image segmentation, the shortage of labeled data is the fundamental problem. How to effectively learn image features from unlabeled images to improve segmentation accuracy is the main research…

The language acquisition literature shows that children do not build their lexicon by segmenting the spoken input into phonemes and then building up words from them, but rather adopt a top-down approach and start by segmenting word-like…

Using more test-time computation during language model inference, such as generating more intermediate thoughts or sampling multiple candidate answers, has proven effective in significantly improving model performance. This paper takes an…

Annotation scarcity has become a major obstacle for training powerful deep-learning models for medical image segmentation, restricting their deployment in clinical scenarios. To address it, semi-supervised learning by exploiting abundant…

We propose an approach for pre-training speech representations via a masked reconstruction loss. Our pre-trained encoder networks are bidirectional and can therefore be used directly in typical bidirectional speech recognition models. The…

Learning sentence embeddings often requires a large amount of labeled data. However, for most tasks and domains, labeled data is seldom available and creating it is expensive. In this work, we present a new state-of-the-art unsupervised…

The dominant automatic lexical stress detection method is to split the utterance into syllable segments using phoneme sequence and their time-aligned boundaries. Then we extract features from syllable to use classification method to…

Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data. Among various methods, contrastive learning learns a discriminative representation by constructing positive and…

Recently, conditional score-based diffusion models have gained significant attention in the field of supervised speech enhancement, yielding state-of-the-art performance. However, these methods may face challenges when generalising to…

In this paper, we aim to improve the performance of semantic image segmentation in a semi-supervised setting in which training is effectuated with a reduced set of annotated images and additional non-annotated images. We present a method…

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing…

Self-supervised pre-trained transformers have improved the state of the art on a variety of speech tasks. Due to the quadratic time and space complexity of self-attention, they usually operate at the level of relatively short (e.g.,…

Speech contains information that is clinically relevant to some diseases, which has the potential to be used for health assessment. Recent work shows an interest in applying deep learning algorithms, especially pretrained large speech…

In this paper, we present our overall efforts to improve the performance of a code-switching speech recognition system using semi-supervised training methods from lexicon learning to acoustic modeling, on the South East Asian…

We present PECMAE, an interpretable model for music audio classification based on prototype learning. Our model is based on a previous method, APNet, which jointly learns an autoencoder and a prototypical network. Instead, we propose to…

We learn audio representations by solving a novel self-supervised learning task, which consists of predicting the phase of the short-time Fourier transform from its magnitude. A convolutional encoder is used to map the magnitude spectrum of…