Leveraging Speaker Embeddings In End-to-end Neural Diarization For Two-speaker Scenarios

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyalvareztrejos2024leveraging

Related papers

• Speaker Embedding-aware Neural Diarization: An Efficient Framework For Overlapping Speech Diarization In Meeting Scenarios (2022)0.00
• Advancing The Dimensionality Reduction Of Speaker Embeddings For Speaker Diarisation: Disentangling Noise And Informing Speech Activity (2021)2.26
• Speakers Unembedded: Embedding-free Approach To Long-form Neural Diarization (2024)3.58
• Speaker Embedding-aware Neural Diarization For Flexible Number Of Speakers With Textual Information (2021)0.00
• EEND-DEMUX: End-to-end Neural Speaker Diarization Via Demultiplexed Speaker Embeddings (2023)0.00
• Speaker Diarization Using Deep Recurrent Convolutional Neural Networks For Speaker Embeddings (2017)9.41
• End-to-end Neural Diarization: Reformulating Speaker Diarization As Simple Multi-label Classification (2020)0.00
• End-to-end Speaker Diarization As Post-processing (2020)11.08