Related papers: Biased Self-supervised learning for ASR

Unsupervised representation learning has recently helped automatic speech recognition (ASR) to tackle tasks with limited labeled data. Following this, hardware limitations and applications give rise to the question how to take advantage of…

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…

Speech evaluation measures a learners oral proficiency using automatic models. Corpora for training such models often pose sparsity challenges given that there often is limited scored data from teachers, in addition to the score…

Speech enhancement (SE) is usually required as a front end to improve the speech quality in noisy environments, while the enhanced speech might not be optimal for automatic speech recognition (ASR) systems due to speech distortion. On the…

Masked language modeling (MLM), a self-supervised pretraining objective, is widely used in natural language processing for learning text representations. MLM trains a model to predict a random sample of input tokens that have been replaced…

Recently, end-to-end multi-speaker text-to-speech (TTS) systems gain success in the situation where a lot of high-quality speech plus their corresponding transcriptions are available. However, laborious paired data collection processes…

Deep neural networks achieve remarkable performances on a wide range of tasks with the aid of large-scale labeled datasets. Yet these datasets are time-consuming and labor-exhaustive to obtain on realistic tasks. To mitigate the requirement…

Dual learning is a paradigm for semi-supervised machine learning that seeks to leverage unsupervised data by solving two opposite tasks at once. In this scheme, each model is used to generate pseudo-labels for unlabeled examples that are…

The ground truth used for training image, video, or speech quality prediction models is based on the Mean Opinion Scores (MOS) obtained from subjective experiments. Usually, it is necessary to conduct multiple experiments, mostly with…

Automatic speech recognition (ASR) of single channel far-field recordings with an unknown number of speakers is traditionally tackled by cascaded modules. Recent research shows that end-to-end (E2E) multi-speaker ASR models can achieve…

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition that encompasses a wide variety of symptoms and degrees of impairment, which makes the diagnosis and treatment challenging. Functional magnetic resonance imaging (fMRI) has…

In recent years, self-supervised learning has attracted widespread academic debate and addressed many of the key issues of computer vision. The present research focus is on how to construct a good agent task that allows for improved network…

This paper presents an audio visual automatic speech recognition (AV-ASR) system using a Transformer-based architecture. We particularly focus on the scene context provided by the visual information, to ground the ASR. We extract…

Compressing self-supervised models has become increasingly necessary, as self-supervised models become larger. While previous approaches have primarily focused on compressing the model size, shortening sequences is also effective in…

Speaker-attributed automatic speech recognition (SA-ASR) in multi-party meeting scenarios is one of the most valuable and challenging ASR task. It was shown that single-channel frame-level diarization with serialized output training…

Large Language Models (LLMs) are discovered to suffer from accurately retrieving key information. To address this, we propose Mask-Enhanced Autoregressive Prediction (MEAP), a simple yet effective training paradigm that seamlessly…

A successful paradigm in representation learning is to perform self-supervised pretraining using tasks based on mini-batch statistics (e.g., SimCLR, VICReg, SwAV, MSN). We show that in the formulation of all these methods is an overlooked…

Fine-tuning a visual pre-trained model can leverage the semantic information from large-scale pre-training data and mitigate the over-fitting problem on downstream vision tasks with limited training examples. While the problem of…

Recent Speech Large Language Models~(LLMs) have achieved impressive capabilities in end-to-end speech interaction. However, the prevailing autoregressive paradigm imposes strict serial constraints, limiting generation efficiency and…

Self-supervised learning (SSL) based models have been shown to generate powerful representations that can be used to improve the performance of downstream speech tasks. Several state-of-the-art SSL models are available, and each of these…