Leveraging Speaker Embeddings in End-to-End Neural Diarization for Two-Speaker Scenarios
Not on the map. Why?
Abstract (arXiv)
End-to-end neural speaker diarization systems are able to address the speaker diarization task while effectively handling speech overlap. This work explores the incorporation of speaker information embeddings into the end-to-end systems to enhance the speaker discriminative capabilities, while maintaining their overlap handling strengths. To achieve this, we propose several methods for incorporating these embeddings along the acoustic features. Furthermore, we delve into an analysis of the correct handling of silence frames, the window length for extracting speaker embeddings and the transformer encoder size. The effectiveness of our proposed approach is thoroughly evaluated on the CallHome dataset for the two-speaker diarization task, with results that demonstrate a significant reduction in diarization error rates achieving a relative improvement of a 10.78% compared to the baseline end-to-end model.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 46 references that are in the map. First posted on arXiv 1 Jul 2024.
Builds on
28 of 46 references.
References · 28
- 2018VoxCeleb2: Deep Speaker Recognitioncited by 862
- 2017VoxCeleb: a large-scale speaker identification datasetcited by 714
- 2015MUSAN: A Music, Speech, and Noise Corpuscited by 400
- 2017Generalized End-to-End Loss for Speaker Verificationcited by 290
- 2016Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separationcited by 189
- 2021A Review of Speaker Diarization: Recent Advances with Deep Learningcited by 122
- 2019End-to-End Neural Speaker Diarization with Permutation-Free Objectivescited by 86
- 2019End-to-End Neural Speaker Diarization with Self-attentioncited by 74
- 2017Speaker Diarization with LSTMcited by 73
- 2020End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractorscited by 70
- 2020Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: theory, implementation and analysis on standard taskscited by 69
- 2020Target-Speaker Voice Activity Detection: a Novel Approach for Multi-Speaker Diarization in a Dinner Party Scenariocited by 67
16 more
- 2021ECAPA-TDNN Embeddings for Speaker Diarizationcited by 47
- 2020Integrating end-to-end neural and clustering-based diarization: Getting the best of both worldscited by 33
- 2021Turn-to-Diarize: Online Speaker Diarization Constrained by Transformer Transducer Speaker Turn Detectioncited by 31
- 2021Encoder-Decoder Based Attractors for End-to-End Neural Diarizationcited by 20
- 2022From Simulated Mixtures to Simulated Conversations as Training Data for End-to-End Neural Diarizationcited by 20
- 2019Probing the Information Encoded in X-vectorscited by 18
- 2020End-to-End Neural Diarization: Reformulating Speaker Diarization as Simple Multi-label Classificationcited by 12
- 2021End-to-end Neural Diarization: From Transformer to Conformercited by 12
- 2022EEND-SS: Joint End-to-End Neural Speaker Diarization and Speech Separation for Flexible Number of Speakerscited by 10
- 2022Augmenting Transformer-Transducer Based Speaker Change Detection With Token-Level Training Losscited by 8
- 2022Target Speaker Voice Activity Detection with Transformers and Its Integration with End-to-End Neural Diarizationcited by 7
- 2021Multi-scale speaker embedding-based graph attention networks for speaker diarisationcited by 6
- 2023Attention-based Encoder-Decoder Network for End-to-End Neural Speaker Diarization with Target Speaker Attractorcited by 4
- 2023An Experimental Review of Speaker Diarization methods with application to Two-Speaker Conversational Telephone Speech recordingscited by 4
- 2023Frame-wise and overlap-robust speaker embeddings for meeting diarizationcited by 2
- 2023Improving Transformer-based End-to-End Speaker Diarization by Assigning Auxiliary Losses to Attention Headscited by 1
Built on by
Not cited yet.