WHAMR!

The 'WHAMR!' dataset/benchmark contains a collection of mixed speech signals designed to evaluate the performance of speech separation algorithms in challenging acoustic environments.

Papers using WHAMR! (24)

Exploring Self-attention Mechanisms For Speech Separation2022 · 46 citesExploring The Integration Of Speech Separation And Recognition With Self-supervised Learning Representation2023 · 8 citesReceptive Field Analysis Of Temporal Convolutional Networks For Monaural Speech Dereverberation2022 · 6 citesOn Time Domain Conformer Models For Monaural Speech Separation In Noisy Reverberant Acoustic Environments2023 · 5 citesLibriheavymix: A 20,000-hour Dataset For Single-channel Reverberant Multi-talker Speech Separation, ASR And Speaker Diarization2024 · 4 citesMagnitude-phase Dual-path Speech Enhancement Network Based On Self-supervised Embedding And Perceptual Contrast Stretch Boosting2025 · 1 citesAsymmetric Encoder-Decoder Based on Time-Frequency Correlation for Speech Separation2026Moving Speaker Separation via Parallel Spectral-Spatial Processing2026MC-LExt: Multi-Channel Target Speaker Extraction with Onset-Prompted Speaker Conditioning Mechanism2025ReFESS-QI: Reference-Free Evaluation For Speech Separation With Joint Quality And Intelligibility Scoring2025Listen to Extract: Onset-Prompted Target Speaker Extraction2025Magnitude-Phase Dual-Path Speech Enhancement Network based on Self-Supervised Embedding and Perceptual Contrast Stretch Boosting2025 · 1 citesA Two-stage Speaker Extraction Algorithm Under Adverse Acoustic Conditions Using A Single-microphone2023TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation2022 · 3 citesOn Data Sampling Strategies for Training Neural Network Speech Separation Models2023 · 1 citesExploring the Integration of Speech Separation and Recognition with Self-Supervised Learning Representation2023 · 1 citesMossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation2023 · 1 citesBSS-CFFMA: Cross-Domain Feature Fusion and Multi-Attention Speech Enhancement Network based on Self-Supervised Embedding2024 · 1 citesUSEF-TSE: Universal Speaker Embedding Free Target Speaker Extraction2024 · 1 citesDeformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation2022A two-stage speaker extraction algorithm under adverse acoustic conditions using a single-microphone2023On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments2023LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization2024X-CrossNet: A complex spectral mapping approach to target speaker extraction with cross attention speaker embedding fusion2024