Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2310.01128

Disentangling Voice and Content with Self-Supervision for Speaker Recognition

Tianchi Liu·Kong Aik Lee·Qiongqiong Wang·Haizhou Li
View original source ↗Read source document ↗Export metadata ↓

Abstract

For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker traits and content variability in speech. It is realized with the use of three Gaussian inference layers, each consisting of a learnable transition model that extracts distinct speech components. Notably, a strengthened transition model is specifically designed to model complex speech dynamics. We also propose a self-supervision method to dynamically disentangle content without the use of labels other than speaker identities. The efficacy of the proposed framework is validated via experiments conducted on the VoxCeleb and SITW datasets with 9.56% and 8.24% average reductions in EER and minDCF, respectively. Since neither additional model training nor data is specifically needed, it is easily applicable in practical use.

Explore related subjects

eess.AScs.AI

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Tianchi Liu, Kong Aik Lee, Qiongqiong Wang, Haizhou Li. 2023-11-01. Disentangling Voice and Content with Self-Supervision for Speaker Recognition. https://arxiv.org/abs/2310.01128

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Pruning as Regularization: Sensitivity-Aware One-Shot Pruning in ASR

We challenge the conventional view of neural network pruning as solely a compression technique, demonstrating that one-shot magnitude pruning serves as a powerful implicit regularizer for ASR. Using Whisper-small, we combine gradient- and Fisher-based sensitivity diagnostics with targeted, component-wise pruning. This reveals architectural asymmetries: decoder FFNs are pruning-fragile, whereas decoder self-attention and the last encoder layers contain redundancy that, when removed, improves generalization. Without fine-tuning, pruning 50% of decoder self-attention reduces WER by 2.38% absolute (20.44% relative) on LibriSpeech test-other; pruning the last four encoder layers at 50% instead yields a 1.72% absolute (14.8% relative) improvement. Gains persisted on Common Voice and TED-LIUM datasets. Beyond regularization benefits, our sensitivity-aware approach enables more aggressive one-shot compression. At 40% sparsity, where established global pruning approaches catastrophically fail, our method preserves near-baseline accuracy. This positions pruning as a first-class architectural design tool: knowing where to prune is as important as how much to prune.

eess.AS↗
arXiv2026

Review of MEMS Transducers for Audio Applications

Microelectromechanical systems (MEMS) speakers are compact, scalable alternatives to traditional voice coil speakers, promising improved sound quality through precise semiconductor manufacturing. This review provides an overview of the research landscape, covering baseband-displacement, ultrasound-based, and thermoacoustic sound generation concepts, classifying MEMS speakers by their actuation principles as electrodynamic, piezoelectric, or electrostatic devices. A comparative analysis of performance indicators from 1990 to 2026 highlights the dominance of piezoelectric MEMS with baseband displacement, focusing on miniaturization and efficiency. The review outlines upcoming research challenges and identifies potential candidates for achieving full-spectrum audio performance. A focus on innovative approaches could lead to widespread adoption of MEMS-only speakers.

eess.AS↗
arXiv2026

Local Diagnostics of Continuous Normalizing Flow for Out-of-Distribution Detection

We address the problem of out-of-distribution (OOD) detection for target observations embedded in a subspace of the high dimensional data space. Using continuous normalizing flows (CNFs), we propose a Lagrangian sub-flow (LSF) framework designed to isolate and estimate the density for the relevant components in the representation and using the remaining components as context. Through experimentation with models for speech synthesis, we show that CNFs, similarly to other deep generative models (DGMs), are susceptible to the "likelihood paradox", where high likelihood is erroneously assigned to OOD samples. This is attributed to the inductive bias of DGMs that prioritize low-level structural details over high-level semantic coherence. To mitigate this phenomenon, we propose a number of geometric diagnostic signals based on the velocity field over the sub-flow trajectory. Based on these signals, we design metrics for the challenging task of zero-shot phoneme-level mispronunciation detection. Finally, we demonstrate the superiority of these metrics compared to likelihood-based methods on a real-world mispronunciation detection benchmark.

eess.AS↗