相关论文: A comprehensive study on self-supervised distillat…

Fine tuning self supervised pretrained models using pseudo labels can effectively improve speech recognition performance. But, low quality pseudo labels can misguide decision boundaries and degrade performance. We propose a simple yet…

The landscape of self-supervised learning (SSL) is currently dominated by generative approaches (e.g., MAE) that reconstruct raw low-level data, and predictive approaches (e.g., I-JEPA) that predict high-level abstract embeddings. While…

Although deep learning-based computer-aided diagnosis systems have recently achieved expert-level performance, developing a robust deep learning model requires large, high-quality data with manual annotation, which is expensive to obtain.…

In this paper, we propose a new Self-Supervised Learning (SSL) algorithm called data2vec-aqc, for speech representation learning from unlabeled speech data. Our goal is to improve SSL for speech in domains where both unlabeled and labeled…

Continuous speech representations based on Variational Autoencoders (VAEs) have emerged as a promising alternative to traditional spectrogram or discrete token based features for speech generation and reconstruction. Recent research has…

We propose utilizing n-best reranking to enhance Sequence-Level Knowledge Distillation (Kim and Rush, 2016) where we extract pseudo-labels for student model's training data from top n-best hypotheses and leverage a diverse set of models…

We investigate the feasibility of sequence-level knowledge distillation of Sequence-to-Sequence (Seq2Seq) models for Large Vocabulary Continuous Speech Recognition (LVSCR). We first use a pre-trained larger teacher model to generate…

In recent years, self-supervised learning paradigm has received extensive attention due to its great success in various down-stream tasks. However, the fine-tuning strategies for adapting those pre-trained models to speaker verification…

The advancements in disentangled representation learning significantly enhance the accuracy of counterfactual predictions by granting precise control over instrumental variables, confounders, and adjustable variables. An appealing method…

A prominent technique for self-supervised representation learning has been to contrast semantically similar and dissimilar pairs of samples. Without access to labels, dissimilar (negative) points are typically taken to be randomly sampled…

Transformer-based speech self-supervised learning (SSL) models, such as HuBERT, show surprising performance in various speech processing tasks. However, huge number of parameters in speech SSL models necessitate the compression to a more…

In recent years, the rapid progress in speaker verification (SV) technology has been driven by the extraction of speaker representations based on deep learning. However, such representations are still vulnerable to emotion variability. To…

Contrastive learning enables learning useful audio and speech representations without ground-truth labels by maximizing the similarity between latent representations of similar signal segments. In this framework various data augmentation…

We propose an approach for training speaker identification models in a weakly supervised manner. We concentrate on the setting where the training data consists of a set of audio recordings and the speaker annotation is provided only at the…

The ability of learning from noisy labels is very useful in many visual recognition tasks, as a vast amount of data with noisy labels are relatively easy to obtain. Traditionally, the label noises have been treated as statistical outliers,…

This paper proposes a powerful Visual Speech Recognition (VSR) method for multiple languages, especially for low-resource languages that have a limited number of labeled data. Different from previous methods that tried to improve the VSR…

We introduce DiceHuBERT, a knowledge distillation framework for compressing HuBERT, a widely used self-supervised learning (SSL)-based speech foundation model. Unlike existing distillation methods that rely on layer-wise and feature-wise…

The large amount of audiovisual content being shared online today has drawn substantial attention to the prospect of audiovisual self-supervised learning. Recent works have focused on each of these modalities separately, while others have…

Distance Metric Learning (DML) has typically dominated the audio-visual speaker verification problem space, owing to strong performance in new and unseen classes. In our work, we explored multitask learning techniques to further enhance…

The deep learning models used for speaker verification rely heavily on large amounts of data and correct labeling. However, noisy (incorrect) labels often occur, which degrades the performance of the system. In this paper, we propose a…