相关论文: The Effect of Batch Size on Contrastive Self-Super…

Self-supervised learning of speech representations has been a very active research area but most work is focused on a single domain such as read audio books for which there exist large quantities of labeled and unlabeled data. In this…

Self-supervised pre-training methods based on contrastive learning or regression tasks can utilize more unlabeled data to improve the performance of automatic speech recognition (ASR). However, the robustness impact of combining the two…

While scaling laws for large language models (LLMs) during pre-training have been extensively studied, their behavior under reinforcement learning (RL) post-training remains largely unexplored. This paper presents a systematic empirical…

Recent work in the field of speech enhancement (SE) has involved the use of self-supervised speech representations (SSSRs) as feature transformations in loss functions. However, in prior work, very little attention has been paid to the…

With limited high-quality data and growing compute, multi-epoch training is gaining back its importance across sub-areas of deep learning. Adam(W), versions of which are go-to optimizers for many tasks such as next token prediction, has two…

Large Language Models are affected by the phenomena of memorizing and forgetting their training data. But how do these vary by model size? We work towards this question by investigating how the model size affects the model's ability to…

Large language models have been proven quite beneficial for a variety of automatic speech recognition tasks in Google. We summarize results on Voice Search and a few YouTube speech transcription tasks to highlight the impact that one can…

We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler. wav2vec 2.0 masks the…

Wav2vec-C introduces a novel representation learning technique combining elements from wav2vec 2.0 and VQ-VAE. Our model learns to reproduce quantized representations from partially masked speech encoding using a contrastive loss in a way…

We introduce Predictive Batch Scheduling (PBS), a novel training optimization technique that accelerates language model convergence by dynamically prioritizing high-loss samples during batch construction. Unlike curriculum learning…

Multi-Modal Self-Supervised Learning from videos has been shown to improve model's performance on various downstream tasks. However, such Self-Supervised pre-training requires large batch sizes and a large amount of computation resources…

Although the pre-training followed by fine-tuning paradigm is used extensively in many fields, there is still some controversy surrounding the impact of pre-training on the fine-tuning process. Currently, experimental findings based on text…

For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively…

Large-scale training corpora have significantly improved the performance of ASR models. Unfortunately, due to the relative scarcity of data, Chinese accents and dialects remain a challenge for most ASR models. Recent advancements in…

Reasoning is an integral part of many tasks performed by language models (LMs). However, the effects of scaling model sizes and data on reasoning abilities at pretraining time remain understudied. To rigorously investigate this problem, we…

Multi-scale resolution training has seen an increased adoption across multiple vision tasks, including classification and detection. Training with smaller resolutions enables faster training at the expense of a drop in accuracy. Conversely,…

Enhancing speech quality is an indispensable yet difficult task as it is often complicated by a range of degradation factors. In addition to additive noise, reverberation, clipping, and speech attenuation can all adversely affect speech…

This paper explores the use of Dutch archival television broadcast data for self-supervised learning of speech foundation models, specifically wav2vec 2.0. We first study data quality assumptions for pre-training, and show how music, noise…

Generative models have gained more and more attention in recent years for their remarkable success in tasks that required estimating and sampling data distribution to generate high-fidelity synthetic data. In speech, text-to-speech…

The past few years have seen remarkable progress in the decoding of speech from brain activity, primarily driven by large single-subject datasets. However, due to individual variation, such as anatomy, and differences in task design and…