paper-with-me

홈 › Papers

DiaPer: End-to-End Neural Diarization with Perceiver-Based Attractors

2023-12-07 · Federico Landini, Mireia Diez, Themos Stafylakis, Lukáš Burget

Until recently, the field of speaker diarization was dominated by cascaded systems. Due to their limitations, mainly regarding overlapped speech and cumbersome pipelines, end-to-end models have gained great popularity lately. One of the most successful models is end-to-end neural diarization with encoder-decoder based attractors (EEND-EDA). In this work, we replace the EDA module with a Perceiver-based one and show its advantages over EEND-EDA; namely obtaining better performance on the largely studied Callhome dataset, finding the quantity of speakers in a conversation more accurately, and faster inference time. Furthermore, when exhaustively compared with other methods, our model, DiaPer, reaches remarkable performance with a very lightweight design. Besides, we perform comparisons with other works and a cascaded baseline across more than ten public wide-band datasets. Together with this publication, we release the code of DiaPer as well as models trained on public and free data.

📄 PDF Abstract BibTeX arXiv:2312.04324

Code (1)

butspeechfit/diaper 공식 구현 pytorch

Tasks

Decoderspeaker-diarizationSpeaker Diarization

Similar Papers 제목 키워드 기반

Neural Speaker Diarization via Multilingual Training: Evaluation on Low-Resource Nepali-Hindi Speech

2026-06-21 · Samip Neupane, Sandesh Pokhrel, Sandesh Pyakurel, Basanta Joshi arxiv

Speaker diarization, the task of determining "who spoke when" in a multi-speaker recording, is a critical component in applications such as meeting transcription, accessibility tools, and multilingual information retriev…

Information RetrievalSpeaker Diarization

From Modular to End-to-End Speaker Diarization

2024-06-27 · Federico Landini

Speaker diarization is usually referred to as the task that determines ``who spoke when'' in a recording. Until a few years ago, all competitive approaches were modular. Systems based on this framework reached state-of-t…

speaker-diarizationSpeaker Diarization

Encoder-Decoder Based Attractors for End-to-End Neural Diarization

2021-06-20 · Shota Horiguchi, Yusuke Fujita, Shinji Watanabe, Yawen Xue 외

This paper investigates an end-to-end neural diarization (EEND) method for an unknown number of speakers. In contrast to the conventional cascaded approach to speaker diarization, EEND methods are better in terms of spea…

Decoderspeaker-diarizationSpeaker Diarization

Neural Diarization with Non-autoregressive Intermediate Attractors

2023-03-13 · Yusuke Fujita, Tatsuya Komatsu, Robin Scheibler, Yusuke Kida 외

End-to-end neural diarization (EEND) with encoder-decoder-based attractors (EDA) is a promising method to handle the whole speaker diarization problem simultaneously with a single neural network. While the EEND model can…

Decoderspeaker-diarizationSpeaker Diarization

End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors

2020-05-20 · Shota Horiguchi, Yusuke Fujita, Shinji Watanabe, Yawen Xue 외

End-to-end speaker diarization for an unknown number of speakers is addressed in this paper. Recently proposed end-to-end speaker diarization outperformed conventional clustering-based speaker diarization, but it has one…

ClusteringDecoderspeaker-diarizationSpeaker Diarization