Related papers: DQ-Data2vec: Decoupling Quantization for Multiling…

Children's speech presents challenges for age and gender classification due to high variability in pitch, articulation, and developmental traits. While self-supervised learning (SSL) models perform well on adult speech tasks, their ability…

This paper explores the use of Dutch archival television broadcast data for self-supervised learning of speech foundation models, specifically wav2vec 2.0. We first study data quality assumptions for pre-training, and show how music, noise…

Discretization of semantic features enables interoperability between semantic and digital communication systems, showing significant potential for practical applications. The fundamental difficulty in digitizing semantic features stems from…

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…

In conventional deep speaker embedding frameworks, the pooling layer aggregates all frame-level features over time and computes their mean and standard deviation statistics as inputs to subsequent segment-level layers. Such statistics…

Relationships in scientific data, such as the numerical and spatial distribution relations of features in univariate data, the scalar-value combinations' relations in multivariate data, and the association of volumes in time-varying and…

Most state-of-the-art Deep Learning systems for speaker verification are based on speaker embedding extractors. These architectures are commonly composed of a feature extractor front-end together with a pooling layer to encode…

Self-supervised learning (SSL) of speech representations has received much attention over the last few years but most work has focused on languages and domains with an abundance of unlabeled data. However, for many languages there is a…

Deep learning-based semantic communication has largely relied on analog or semi-digital transmission, which limits compatibility with modern digital communication infrastructures. Recent studies have employed vector quantization (VQ) to…

Domain mismatch problem caused by speaker-unrelated feature has been a major topic in speaker recognition. In this paper, we propose an explicit disentanglement framework to unravel speaker-relevant features from speaker-unrelated features…

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…

Preserving a patient's identity is a challenge for automatic, speech-based diagnosis of mental health disorders. In this paper, we address this issue by proposing adversarial disentanglement of depression characteristics and speaker…

Recent techniques for speech deepfake detection often rely on pre-trained self-supervised models. These systems, initially developed for Automatic Speech Recognition (ASR), have proved their ability to offer a meaningful representation of…

Diffusion large language models (dLLMs), which offer bidirectional context and flexible masked-denoising generation, are emerging as a compelling alternative to autoregressive (AR) LLMs. However, like AR LLMs, their model sizes continue to…

Discrete representations of speech, obtained from Self-Supervised Learning (SSL) foundation models, are widely used, especially where there are limited data for the downstream task, such as for a low-resource language. Typically,…

We propose a novel approach to semi-supervised automatic speech recognition (ASR). We first exploit a large amount of unlabeled audio data via representation learning, where we reconstruct a temporal slice of filterbank features from past…

Zero-shot voice conversion is a technique that alters the speaker identity of an input speech to match a target speaker using only a single reference utterance, without requiring additional training. Recent approaches extensively utilize…

Speech tokenizers serve as foundational components for speech language models, yet current designs exhibit several limitations, including: 1) dependence on multi-layer residual vector quantization structures or high frame rates, 2) reliance…

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…

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the…