paper-with-me

홈 › Papers

Probabilistic Back-ends for Online Speaker Recognition and Clustering

2023-02-19 · Alexey Sholokhov, Nikita Kuzmin, Kong Aik Lee, Eng Siong Chng

This paper focuses on multi-enrollment speaker recognition which naturally occurs in the task of online speaker clustering, and studies the properties of different scoring back-ends in this scenario. First, we show that popular cosine scoring suffers from poor score calibration with a varying number of enrollment utterances. Second, we propose a simple replacement for cosine scoring based on an extremely constrained version of probabilistic linear discriminant analysis (PLDA). The proposed model improves over the cosine scoring for multi-enrollment recognition while keeping the same performance in the case of one-to-one comparisons. Finally, we consider an online speaker clustering task where each step naturally involves multi-enrollment recognition. We propose an online clustering algorithm allowing us to take benefits from the PLDA model such as the ability to handle uncertainty and better score calibration. Our experiments demonstrate the effectiveness of the proposed algorithm.

📄 PDF Abstract BibTeX arXiv:2302.09523

Code (1)

sholokhovalexey/online-speaker-clustering 공식 구현 pytorch

Tasks

ClusteringOnline ClusteringSpeaker Recognition

Similar Papers 제목 키워드 기반

Graph Neural Network Backend for Speaker Recognition

2023-08-17 · Liang He, Ruida Li, Mengqi Niu

Currently, most speaker recognition backends, such as cosine, linear discriminant analysis (LDA), or probabilistic linear discriminant analysis (PLDA), make decisions by calculating similarity or distance between enrollm…

Graph Neural NetworkSpeaker Recognition

Toroidal Probabilistic Spherical Discriminant Analysis

2022-10-27 · Anna Silnova, Niko Brümmer, Albert Swart, Lukáš Burget

In speaker recognition, where speech segments are mapped to embeddings on the unit hypersphere, two scoring back-ends are commonly used, namely cosine scoring and PLDA. We have recently proposed PSDA, an analog to PLDA t…

FormSpeaker Recognition

Scoring of Large-Margin Embeddings for Speaker Verification: Cosine or PLDA?

2022-04-08 · Qiongqiong Wang, Kong Aik Lee, Tianchi Liu

The emergence of large-margin softmax cross-entropy losses in training deep speaker embedding neural networks has triggered a gradual shift from parametric back-ends to a simpler cosine similarity measure for speaker ver…

Speaker Verification

Probabilistic Spherical Discriminant Analysis: An Alternative to PLDA for length-normalized embeddings

2022-03-28 · Niko Brümmer, Albert Swart, Ladislav Mošner, Anna Silnova 외

In speaker recognition, where speech segments are mapped to embeddings on the unit hypersphere, two scoring backends are commonly used, namely cosine scoring or PLDA. Both have advantages and disadvantages, depending on …

Speaker Recognition

NPLDA: A Deep Neural PLDA Model for Speaker Verification

2020-02-10 · Shreyas Ramoji, Prashant Krishnan, Sriram Ganapathy

The state-of-art approach for speaker verification consists of a neural network based embedding extractor along with a backend generative model such as the Probabilistic Linear Discriminant Analysis (PLDA). In this work,…

Speaker RecognitionSpeaker Verification