Related papers: Reduce, Reuse, Recycle: Is Perturbed Data better t…

Large, pre-trained representation models trained using self-supervised learning have gained popularity in various fields of machine learning because they are able to extract high-quality salient features from input data. As such, they have…

Self-supervised pre-training of a speech foundation model, followed by supervised fine-tuning, has shown impressive quality improvements on automatic speech recognition (ASR) tasks. Fine-tuning separate foundation models for many downstream…

Cross-lingual speech adaptation aims to solve the problem of leveraging multiple rich-resource languages to build models for a low-resource target language. Since the low-resource language has limited training data, speech recognition…

Building Automatic Speech Recognition (ASR) systems for code-switched speech has recently gained renewed attention due to the widespread use of speech technologies in multilingual communities worldwide. End-to-end ASR systems are a natural…

Large language models (LLMs) have demonstrated potential in handling spoken inputs for high-resource languages, reaching state-of-the-art performance in various tasks. However, their applicability is still less explored in low-resource…

The use of synthetic speech as data augmentation is gaining increasing popularity in fields such as automatic speech recognition and speech classification tasks. Despite novel text-to-speech systems with voice cloning capabilities, that…

Large Audio Language Models (LALMs) have emerged as powerful tools for speech-related tasks but remain underexplored for fine-tuning, especially with limited speech data. To bridge this gap, we systematically examine how different…

We examine the effect of data augmentation for training of language models for speech recognition. We compare augmentation based on global error statistics with one based on per-word unigram statistics of ASR errors and observe that it is…

Varying data augmentation policies and regularization over the course of optimization has led to performance improvements over using fixed values. We show that population based training is a useful tool to continuously search those…

Recent speech technologies have led to produce high quality synthesised speech due to recent advances in neural Text to Speech (TTS). However, such TTS models depend on extensive amounts of data that can be costly to produce and is hardly…

Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and…

Existing Speech Language Model (SLM) scaling analysis paints a bleak picture. It predicts that SLMs require much more compute and data compared to text, leading some to question the feasibility of training high-quality SLMs. However, modern…

Self-supervised learning (SSL) has grown in interest within the speech processing community, since it produces representations that are useful for many downstream tasks. SSL uses global and contextual methods to produce robust…

Multilingual speech processing with self-supervised or supervised pre-trained Speech Foundation Models (SFM) has achieved strong performance on tasks like Language Identification (LID) and Automatic Speech Recognition (ASR). However, these…

Automated speaking assessment (ASA) on opinion expressions is often hampered by the scarcity of labeled recordings, which restricts prompt diversity and undermines scoring reliability. To address this challenge, we propose a novel training…

Data augmentation methods usually apply the same augmentation (or a mix of them) to all the training samples. For example, to perturb data with noise, the noise is sampled from a Normal distribution with a fixed standard deviation, for all…

Self-supervised learning (SSL) methods have proven to be very successful in automatic speech recognition (ASR). These great improvements have been reported mostly based on highly curated datasets such as LibriSpeech for non-streaming…

Self-supervised learning (SSL) is a long-standing goal for speech processing, since it utilizes large-scale unlabeled data and avoids extensive human labeling. Recent years witness great successes in applying self-supervised learning in…

The cross-domain performance of automatic speech recognition (ASR) could be severely hampered due to the mismatch between training and testing distributions. Since the target domain usually lacks labeled data, and domain shifts exist at…

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…