TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Methods/EEND

EEND

End-to-End Neural Diarization

AudioIntroduced 200026 papers
Source Paper

Description

End-to-End Neural Diarization is a neural network for speaker diarization in which a neural network directly outputs speaker diarization results given a multi-speaker recording. To realize such an end-to-end model, the speaker diarization problem is formulated as a multi-label classification problem and a permutation-free objective function is introduced to directly minimize diarization errors. The EEND method can explicitly handle speaker overlaps during training and inference. Just by feeding multi-speaker recordings with corresponding speaker segment labels, the model can be adapted to real conversations.

Papers Using This Method

LS-EEND: Long-Form Streaming End-to-End Neural Diarization with Online Attractor Extraction2024-10-09From Modular to End-to-End Speaker Diarization2024-06-27Speakers Unembedded: Embedding-free Approach to Long-form Neural Diarization2024-06-26Song Data Cleansing for End-to-End Neural Singer Diarization Using Neural Analysis and Synthesis Framework2024-06-24Powerset multi-class cross entropy loss for neural speaker diarization2023-10-19Frame-wise and overlap-robust speaker embeddings for meeting diarization2023-06-01An Experimental Review of Speaker Diarization methods with application to Two-Speaker Conversational Telephone Speech recordings2023-05-29Neural Diarization with Non-autoregressive Intermediate Attractors2023-03-13TOLD: A Novel Two-Stage Overlap-Aware Framework for Speaker Diarization2023-03-08BER: Balanced Error Rate For Speaker Diarization2022-11-08Utterance-by-utterance overlap-aware neural diarization with Graph-PIT2022-07-28Online Neural Diarization of Unlimited Numbers of Speakers Using Global and Local Attractors2022-06-06Improving the Naturalness of Simulated Conversations for End-to-End Neural Diarization2022-04-24Low-Latency Speech Separation Guided Diarization for Telephone Conversations2022-04-05From Simulated Mixtures to Simulated Conversations as Training Data for End-to-End Neural Diarization2022-04-02Tight integration of neural- and clustering-based diarization through deep unfolding of infinite Gaussian mixture model2022-02-14ASR-Aware End-to-end Neural Diarization2022-02-02Auxiliary Loss of Transformer with Residual Connection for End-to-End Speaker Diarization2021-10-14Multi-Channel End-to-End Neural Diarization with Distributed Microphones2021-10-10Encoder-Decoder Based Attractors for End-to-End Neural Diarization2021-06-20