LibriCSS

'LibriCSS' is a dataset used to evaluate speech separation performance in realistic acoustic environments, containing recordings of overlapping speakers and background noise.

Papers using LibriCSS (21)

TS-SEP: Joint Diarization And Separation Conditioned On Estimated Speaker Embeddings2023 · 28 citesAn Initialization Scheme For Meeting Separation With Spatial Mixture Models2022 · 10 citesMeeting Recognition With Continuous Speech Separation And Transcription-supported Diarization2023 · 7 citesTF-CorrNet: Leveraging Spatial Correlation for Continuous Speech Separation2025 · 1 citesTS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings2023 · 2 citesAsymmetric Encoder-Decoder Based on Time-Frequency Correlation for Speech Separation2026Elevating Robust Multi-talker ASR By Decoupling Speaker Separation And Speech Recognition2025Elevating Robust Multi-Talker ASR by Decoupling Speaker Separation and Speech Recognition2025Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models2024Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription2023Simultaneous Diarization And Separation Of Meetings Through The Integration Of Statistical Mixture Models2024Combining Tf-gridnet And Mixture Encoder For Continuous Speech Separation For Meeting Transcription2023GPU-accelerated Guided Source Separation for Meeting Transcription2022 · 5 citesMeeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization2023 · 3 citesSURT 2.0: Advances in Transducer-based Multi-talker Speech Recognition2023 · 1 citesDCF-DS: Deep Cascade Fusion of Diarization and Separation for Speech Recognition under Realistic Single-Channel Conditions2024 · 1 citesMMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator2022Multi-resolution location-based training for multi-channel continuous speech separation2023Speaker Change Detection for Transformer Transducer ASR2023Statistical Beamformer Exploiting Non-stationarity and Sparsity with Spatially Constrained ICA for Robust Speech Recognition2023Multi-channel Conversational Speaker Separation via Neural Diarization2023