相关论文: Test-Time Adaptation Toward Personalized Speech En…

In this work, we propose a method to create domain-sensitive speech recognition models that utilize textual domain information by conditioning its generation on a given text prompt. This is accomplished by fine-tuning a pre-trained,…

Diffusion models have achieved remarkable success in generating high-resolution, realistic images across diverse natural distributions. However, their performance heavily relies on high-quality training data, making it challenging to learn…

State-of-the-art speaker verification systems are inherently dependent on some kind of human supervision as they are trained on massive amounts of labeled data. However, manually annotating utterances is slow, expensive and not scalable to…

Audio-visual speech enhancement (AV-SE) aims to enhance degraded speech along with extra visual information such as lip videos, and has been shown to be more effective than audio-only speech enhancement. This paper proposes further…

Recent work on distilling Whisper's knowledge into small models using pseudo-labels shows promising performance while reducing the size by up to 50%. This results in small, efficient, and dedicated models. However, a critical step of…

Existing methods for distillation do not efficiently utilize the training data. This work presents a novel approach to perform distillation using only a subset of the training data, making it more data-efficient. For this purpose, the…

Continual learning refers to a dynamical framework in which a model receives a stream of non-stationary data over time and must adapt to new data while preserving previously acquired knowledge. Unluckily, neural networks fail to meet these…

Knowledge Distillation is a technique which aims to utilize dark knowledge to compress and transfer information from a vast, well-trained neural network (teacher model) to a smaller, less capable neural network (student model) with improved…

Expressive voice conversion aims to transfer both speaker identity and expressive attributes from a target speech to a given source speech. In this work, we improve over a self-supervised, non-autoregressive framework with a conditional…

Pre-training a large transformer model on a massive amount of unlabeled data and fine-tuning it on labeled datasets for diverse downstream tasks has proven to be a successful strategy, for a variety of vision and natural language processing…

The performance of autoregressive models on natural language generation tasks has dramatically improved due to the adoption of deep, self-attentive architectures. However, these gains have come at the cost of hindering inference speed,…

Deep learning models for speech rely on large datasets, presenting computational challenges. Yet, performance hinges on training data size. Dataset Distillation (DD) aims to learn a smaller dataset without much performance degradation when…

This paper proposes a zero-shot text-to-speech (TTS) conditioned by a self-supervised speech-representation model acquired through self-supervised learning (SSL). Conventional methods with embedding vectors from x-vector or global style…

Performing knowledge transfer from a large teacher network to a smaller student is a popular task in modern deep learning applications. However, due to growing dataset sizes and stricter privacy regulations, it is increasingly common not to…

In recent years, there has been a great deal of research in developing end-to-end speech recognition models, which enable simplifying the traditional pipeline and achieving promising results. Despite their remarkable performance…

This paper addresses the limitations of large-scale language models in safety alignment and robustness by proposing a fine-tuning method that combines contrastive distillation with noise-robust training. The method freezes the backbone…

As virtual assistants have become more diverse and specialized, so has the demand for application or brand-specific wake words. However, the wake-word-specific datasets typically used to train wake-word detectors are costly to create. In…

Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of supervision that provides finer descriptions to visual concepts…

Automatically describing audio-visual content with texts, namely video captioning, has received significant attention due to its potential applications across diverse fields. Deep neural networks are the dominant methods, offering…

Self-supervised pre-training is an effective approach to leveraging a large amount of unlabelled data to reduce word error rates (WERs) of automatic speech recognition (ASR) systems. Since it is impractical to use large pre-trained models…