Related papers: DiffSSD: A Diffusion-Based Dataset For Speech Fore…

Synthetic data generation is increasingly used in machine learning for training and data augmentation. Yet, current strategies often rely on external foundation models or datasets, whose usage is restricted in many scenarios due to policy…

Many recently published Text-to-Speech (TTS) systems produce audio close to real speech. However, TTS evaluation needs to be revisited to make sense of the results obtained with the new architectures, approaches and datasets. We propose…

Disentangled representation learning in speech processing has lagged behind other domains, largely due to the lack of datasets with annotated generative factors for robust evaluation. To address this, we propose SynSpeech, a novel…

Diffusion-based generative models have recently gained attention in speech enhancement (SE), providing an alternative to conventional supervised methods. These models transform clean speech training samples into Gaussian noise centered at…

Recent progress in generative AI technology has made audio deepfakes remarkably more realistic. While current research on anti-spoofing systems primarily focuses on assessing whether a given audio sample is fake or genuine, there has been…

Achieving robust generalization in speech deepfake detection (SDD) remains a primary challenge, as models often fail to detect unseen forgery methods. While research has focused on model-centric and algorithm-centric solutions, the impact…

Recent advances in deep learning have enabled the creation of natural-sounding synthesised speech. However, attackers have also utilised these tech-nologies to conduct attacks such as phishing. Numerous public datasets have been created to…

Modern speech synthesis techniques can produce natural-sounding speech given sufficient high-quality data and compute resources. However, such data is not readily available for many languages. This paper focuses on speech synthesis for…

Synthetic data generation is gaining increasing popularity in different computer vision applications. Existing state-of-the-art face recognition models are trained using large-scale face datasets, which are crawled from the Internet and…

Recent advances in artificial speech and audio technologies have improved the abilities of deep-fake operators to falsify media and spread malicious misinformation. Anyone with limited coding skills can use freely available speech synthesis…

Thanks to the growing availability of spoofing databases and rapid advances in using them, systems for detecting voice spoofing attacks are becoming more and more capable, and error rates close to zero are being reached for the ASVspoof2015…

Supervised training of speech recognition models requires access to transcribed audio data, which often is not possible due to confidentiality issues. Our approach to this problem is to generate synthetic audio from a text-only corpus using…

Recent works demonstrate that voice assistants do not perform equally well for everyone, but research on demographic robustness of speech technologies is still scarce. This is mainly due to the rarity of large datasets with controlled…

Building an accurate automatic speech recognition (ASR) system requires a large dataset that contains many hours of labeled speech samples produced by a diverse set of speakers. The lack of such open free datasets is one of the main issues…

The availability of large-scale authentic face databases has been crucial to the significant advances made in face recognition research over the past decade. However, legal and ethical concerns led to the recent retraction of many of these…

Diffusion models have demonstrated significant potential in speech synthesis tasks, including text-to-speech (TTS) and voice cloning. However, their iterative denoising processes are computationally intensive, and previous distillation…

Electromyography-to-Speech (ETS) conversion has demonstrated its potential for silent speech interfaces by generating audible speech from Electromyography (EMG) signals during silent articulations. ETS models usually consist of an EMG…

Diffusion-based speech enhancement (SE) achieves natural-sounding speech and strong generalization, yet suffers from key limitations like generative artifacts and high inference latency. In this work, we systematically study artifact…

We propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representations for speech content, prosodic information, and speaker…

Recent advancements in end-to-end speech synthesis have made it possible to generate highly natural speech. However, training these models typically requires a large amount of high-fidelity speech data, and for unseen texts, the prosody of…