paper-with-me

홈 › Papers

Post-Training Embedding Alignment for Decoupling Enrollment and Runtime Speaker Recognition Models

2024-01-23 · Chenyang Gao, Brecht Desplanques, Chelsea J. -T. Ju, Aman Chadha, Andreas Stolcke

Automated speaker identification (SID) is a crucial step for the personalization of a wide range of speech-enabled services. Typical SID systems use a symmetric enrollment-verification framework with a single model to derive embeddings both offline for voice profiles extracted from enrollment utterances, and online from runtime utterances. Due to the distinct circumstances of enrollment and runtime, such as different computation and latency constraints, several applications would benefit from an asymmetric enrollment-verification framework that uses different models for enrollment and runtime embedding generation. To support this asymmetric SID where each of the two models can be updated independently, we propose using a lightweight neural network to map the embeddings from the two independent models to a shared speaker embedding space. Our results show that this approach significantly outperforms cosine scoring in a shared speaker logit space for models that were trained with a contrastive loss on large datasets with many speaker identities. This proposed Neural Embedding Speaker Space Alignment (NESSA) combined with an asymmetric update of only one of the models delivers at least 60% of the performance gain achieved by updating both models in the standard symmetric SID approach.

📄 PDF Abstract BibTeX arXiv:2401.12440

Code (0)

등록된 구현이 없습니다.

Tasks

Speaker IdentificationSpeaker Recognition

Similar Papers 제목 키워드 기반

Database-Agnostic Gait Enrollment using SetTransformers

2025-05-05 · Nicoleta Basoc, Adrian Cosma, Andy Cǎtrunǎ, Emilian Rǎdoi

Gait recognition has emerged as a powerful tool for unobtrusive and long-range identity analysis, with growing relevance in surveillance and monitoring applications. Although recent advances in deep learning and large-sc…

Gait Recognition

Supervised and Unsupervised Alignments for Spoofing Behavioral Biometrics

2024-08-14 · Thomas Thebaud, Gaël Le Lan, Anthony Larcher

Biometric recognition systems are security systems based on intrinsic properties of their users, usually encoded in high dimension representations called embeddings, which potential theft would represent a greater threat…

Reconstruction AttackSpeaker Verification

Quantitative Evidence on Overlooked Aspects of Enrollment Speaker Embeddings for Target Speaker Separation

2022-10-23 · Xiaoyu Liu, Xu Li, Joan Serrà

Single channel target speaker separation (TSS) aims at extracting a speaker's voice from a mixture of multiple talkers given an enrollment utterance of that speaker. A typical deep learning TSS framework consists of an u…

Speaker IdentificationSpeaker Separation

Diverse Semantics-Guided Feature Alignment and Decoupling for Visible-Infrared Person Re-Identification

2025-05-01 · Neng Dong, Shuanglin Yan, Liyan Zhang, Jinhui Tang

Visible-Infrared Person Re-Identification (VI-ReID) is a challenging task due to the large modality discrepancy between visible and infrared images, which complicates the alignment of their features into a suitable commo…

Person Re-Identification

On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training

2026-01-12 · Xueyan Niu, Bo Bai, Wei Han, Weixi Zhang arxiv

Post-training of large language models routinely interleaves supervised fine-tuning (SFT) with reinforcement learning (RL). These two methods have different objectives: SFT minimizes the cross-entropy loss between model …

Reinforcement Learning