Unsupervised Speaker Diarization that is Agnostic to Language, Overlap-Aware, and Tuning Free
Not on the map. Why?
Abstract (arXiv)
Podcasts are conversational in nature and speaker changes are frequent -- requiring speaker diarization for content understanding. We propose an unsupervised technique for speaker diarization without relying on language-specific components. The algorithm is overlap-aware and does not require information about the number of speakers. Our approach shows 79% improvement on purity scores (34% on F-score) against the Google Cloud Platform solution on podcast data.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 35 references that are in the map. First posted on arXiv 25 Jul 2022.
Builds on
15 of 35 references.
References · 15
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
- 2019pyannote.audio: neural building blocks for speaker diarizationcited by 181
- 2021A Review of Speaker Diarization: Recent Advances with Deep Learningcited by 124
- 2020Spot the conversation: speaker diarisation in the wildcited by 79
- 2019End-to-End Neural Speaker Diarization with Self-attentioncited by 77
- 2017Speaker Diarization with LSTMcited by 73
- 2015End-to-End Text-Dependent Speaker Verificationcited by 49
- 2019Joint Speech Recognition and Speaker Diarization via Sequence Transductioncited by 49
- 2018Fully Supervised Speaker Diarizationcited by 47
- 2019Overlap-aware diarization: resegmentation using neural end-to-end overlapped speech detectioncited by 27
- 2020Speech Recognition and Multi-Speaker Diarization of Long Conversationscited by 23
3 more
- 2020DOVER-Lap: A Method for Combining Overlap-aware Diarization Outputscited by 19
- 2021TREC 2020 Podcasts Track Overviewcited by 13
- 2021Current Challenges and Future Directions in Podcast Information Accesscited by 7
Built on by
Not cited yet.