Related papers: Self-FiLM: Conditioning GANs with self-supervised …
Training a model to perform a task typically requires a large amount of data from the domains in which the task will be applied. However, it is often the case that data are abundant in some domains but scarce in others. Domain adaptation…
Deep learning has brought impressive progress in the study of both automatic speaker verification (ASV) and spoofing countermeasures (CM). Although solutions are mutually dependent, they have typically evolved as standalone sub-systems…
Recent advancements in supervised automatic speech recognition (ASR) have achieved remarkable performance, largely due to the growing availability of large transcribed speech corpora. However, most languages lack sufficient paired speech…
This paper introduces an audio-visual speech enhancement system that leverages score-based generative models, also known as diffusion models, conditioned on visual information. In particular, we exploit audio-visual embeddings obtained from…
This paper makes the first attempt towards unsupervised preference alignment in Vision-Language Models (VLMs). We generate chosen and rejected responses with regard to the original and augmented image pairs, and conduct preference alignment…
Language models (LMs) have shown superior performances in various speech generation tasks recently, demonstrating their powerful ability for semantic context modeling. Given the intrinsic similarity between speech generation and speech…
Classification using supervised learning requires annotating a large amount of classes-balanced data for model training and testing. This has practically limited the scope of applications with supervised learning, in particular deep…
We propose a new strategy to improve the accuracy and robustness of image classification. First, we train a baseline CNN model. Then, we identify challenging regions in the feature space by identifying all misclassified samples, and…
A speaker verification (SV) system offers an authentication service designed to confirm whether a given speech sample originates from a specific speaker. This technology has paved the way for various personalized applications that cater to…
This paper presents our latest investigations on improving automatic speech recognition for noisy speech via speech enhancement. We propose a novel method named Multi-discriminators CycleGAN to reduce noise of input speech and therefore…
We revisit self-training in the context of end-to-end speech recognition. We demonstrate that training with pseudo-labels can substantially improve the accuracy of a baseline model. Key to our approach are a strong baseline acoustic and…
The performance of automatic speech recognition (ASR) systems can be significantly compromised by previously unseen conditions, which is typically due to a mismatch between training and testing distributions. In this paper, we address…
Speaker Verification still suffers from the challenge of generalization to novel adverse environments. We leverage on the recent advancements made by deep learning based speech enhancement and propose a feature-domain supervised denoising…
Self-Supervised Learning (SSL) has allowed leveraging large amounts of unlabeled speech data to improve the performance of speech recognition models even with small annotated datasets. Despite this, speech SSL representations may fail while…
Our prior experiments show that humans and machines seem to employ different approaches to speaker discrimination, especially in the presence of speaking style variability. The experiments examined read versus conversational speech.…
We propose AudioStyleGAN (ASGAN), a new generative adversarial network (GAN) for unconditional speech synthesis. As in the StyleGAN family of image synthesis models, ASGAN maps sampled noise to a disentangled latent vector which is then…
Self-supervised learning (SSL) has shown impressive results in downstream classification tasks. However, there is limited work in understanding their failure modes and interpreting their learned representations. In this paper, we study the…
Advances in automatic speaker verification (ASV) promote research into the formulation of spoofing detection systems for real-world applications. The performance of ASV systems can be degraded severely by multiple types of spoofing attacks,…
Self-supervised learning (SSL) achieves great success in speech recognition, while limited exploration has been attempted for other speech processing tasks. As speech signal contains multi-faceted information including speaker identity,…
This paper is a study of performance-efficiency trade-offs in pre-trained models for automatic speech recognition (ASR). We focus on wav2vec 2.0, and formalize several architecture designs that influence both the model performance and its…