Related papers: Improving Speaker Representations Using Contrastiv…
For fine-grained generation and recognition tasks such as minimally-supervised text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), the intermediate representations extracted from speech should serve as a…
Anti-spoofing is the task of speech authentication. That is, identifying genuine human speech compared to spoofed speech. The main focus of this paper is to suggest new representations for genuine and spoofed speech, based on the…
Speaker diarization systems are challenged by a trade-off between the temporal resolution and the fidelity of the speaker representation. By obtaining a superior temporal resolution with an enhanced accuracy, a multi-scale approach is a way…
The goal of this work is to train robust speaker recognition models without speaker labels. Recent works on unsupervised speaker representations are based on contrastive learning in which they encourage within-utterance embeddings to be…
In general, a self-attention mechanism has been applied for speaker embedding encoding. Previous studies focused on training the self-attention in a high-level layer, such as the last pooling layer. However, the effect of low-level features…
What matters for contrastive learning? We argue that contrastive learning heavily relies on informative features, or "hard" (positive or negative) features. Early works include more informative features by applying complex data…
Contrastive loss has significantly improved performance in supervised classification tasks by using a multi-viewed framework that leverages augmentation and label information. The augmentation enables contrast with another view of a single…
Automatic speaker verification (ASV) systems use a playback detector to filter out playback attacks and ensure verification reliability. Since current playback detection models are almost always trained using genuine and played-back speech,…
Factorizing speech as disentangled speech representations is vital to achieve highly controllable style transfer in voice conversion (VC). Conventional speech representation learning methods in VC only factorize speech as speaker and…
Speaker embedding extractors are typically trained using a classification loss over the training speakers. During the last few years, the standard softmax/cross-entropy loss has been replaced by the margin-based losses, yielding significant…
This paper contains a post-challenge performance analysis on cross-lingual speaker verification of the IDLab submission to the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC-21). We show that current speaker embedding extractors…
Despite the maturity of modern speaker verification technology, its performance still significantly degrades when facing non-neutrally-phonated (e.g., shouted and whispered) speech. To address this issue, in this paper, we propose a new…
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,…
In this work, a novel solution to the speaker identification problem is proposed through minimization of statistical divergences between the probability distribution (g). of feature vectors from the test utterance and the probability…
Given one reference facial image and a piece of speech as input, talking head generation aims to synthesize a realistic-looking talking head video. However, generating a lip-synchronized video with natural head movements is challenging. The…
Contrastive speaker embedding assumes that the contrast between the positive and negative pairs of speech segments is attributed to speaker identity only. However, this assumption is incorrect because speech signals contain not only speaker…
Overlapping sound events are ubiquitous in real-world environments, but existing end-to-end sound event detection (SED) methods still struggle to detect them effectively. A critical reason is that these methods represent overlapping events…
Supervised contrastive learning (SupCon) is widely used to shape representations, but has seen limited targeted study for audio deepfake detection. Existing work typically combines contrastive terms with broader pipelines; however, the…
Although fine-tuning Large Language Models (LLMs) with multilingual data can rapidly enhance the multilingual capabilities of LLMs, they still exhibit a performance gap between the dominant language (e.g., English) and non-dominant ones due…
The front-end factor analysis (FEFA), an extension of principal component analysis (PPCA) tailored to be used with Gaussian mixture models (GMMs), is currently the prevalent approach to extract compact utterance-level features (i-vectors)…