# Magnitude-aware Probabilistic Speaker Embeddings

arXiv: https://arxiv.org/abs/2202.13826 · HTML: https://mlsanity.com/paper/2202.13826/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 28 Feb 2022.

## Builds on (most cited first, 25 of 25)

- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [pyannote.audio: neural building blocks for speaker diarization](https://mlsanity.com/paper/1911.01255/) (2019)
- [Probabilistic Face Embeddings](https://mlsanity.com/paper/1904.09658/) (2019)
- [Data Uncertainty Learning in Face Recognition](https://mlsanity.com/paper/2003.11339/) (2020)
- [In defence of metric learning for speaker recognition](https://mlsanity.com/paper/2003.11982/) (2020)
- [L2-constrained Softmax Loss for Discriminative Face Verification](https://mlsanity.com/paper/1703.09507/) (2017)
- [End-to-end speaker segmentation for overlap-aware resegmentation](https://mlsanity.com/paper/2104.04045/) (2021)
- [Spot the conversation: speaker diarisation in the wild](https://mlsanity.com/paper/2007.01216/) (2020)
- [Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: theory, implementation and analysis on standard tasks](https://mlsanity.com/paper/2012.14952/) (2020)
- [BUT System Description to VoxCeleb Speaker Recognition Challenge 2019](https://mlsanity.com/paper/1910.12592/) (2019)
- [von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning](https://mlsanity.com/paper/2103.15718/) (2021)
- [The Second DIHARD Diarization Challenge: Dataset, task, and baselines](https://mlsanity.com/paper/1906.07839/) (2019)
- [Clova Baseline System for the VoxCeleb Speaker Recognition Challenge 2020](https://mlsanity.com/paper/2009.14153/) (2020)
- [Target-speaker Voice Activity Detection with Improved I-Vector Estimation for Unknown Number of Speaker](https://mlsanity.com/paper/2108.03342/) (2021)
- [Probabilistic embeddings for speaker diarization](https://mlsanity.com/paper/2004.04096/) (2020)
- [Deep Convolutional Neural Network Features and the Original Image](https://mlsanity.com/paper/1611.01751/) (2016)
- [Probabilistic Embeddings Revisited](https://mlsanity.com/paper/2202.06768/) (2022)
- [Look who's not talking](https://mlsanity.com/paper/2011.14885/) (2020)
- [Gaussian meta-embeddings for efficient scoring of a heavy-tailed PLDA model](https://mlsanity.com/paper/1802.09777/) (2018)
- [Fast and Reliable Probabilistic Face Embeddings in the Wild](https://mlsanity.com/paper/2102.04075/) (2021)

## Built on by (most cited first, 3 of 3)

- [Pushing the limits of raw waveform speaker recognition](https://mlsanity.com/paper/2203.08488/) (2022)
- [Probabilistic Back-ends for Online Speaker Recognition and Clustering](https://mlsanity.com/paper/2302.09523/) (2023)
- [ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention](https://mlsanity.com/paper/2305.12121/) (2023)

## Abstract (arXiv)

Recently, hyperspherical embeddings have established themselves as a dominant technique for face and voice recognition. Specifically, Euclidean space vector embeddings are learned to encode person-specific information in their direction while ignoring the magnitude. However, recent studies have shown that the magnitudes of the embeddings extracted by deep neural networks may indicate the quality of the corresponding inputs. This paper explores the properties of the magnitudes of the embeddings related to quality assessment and out-of-distribution detection. We propose a new probabilistic speaker embedding extractor using the information encoded in the embedding magnitude and leverage it in the speaker verification pipeline. We also propose several quality-aware diarization methods and incorporate the magnitudes in those. Our results indicate significant improvements over magnitude-agnostic baselines both in speaker verification and diarization tasks.