WHAMR

The 'WHAMR!' dataset/benchmark contains a collection of mixed speech signals designed to evaluate speech separation algorithms in challenging acoustic environments with overlapping speakers, background noise, and reverberation.

Papers using WHAMR (23)

Magnitude-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 Extraction2025MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions2023 · 64 citesConvolutive Prediction for Monaural Speech Dereverberation and Noisy-Reverberant Speaker Separation2021 · 32 citesUtterance Weighted Multi-Dilation Temporal Convolutional Networks for Monaural Speech Dereverberation2022 · 8 citesReceptive Field Analysis of Temporal Convolutional Networks for Monaural Speech Dereverberation2022 · 6 citesOn Data Sampling Strategies for Training Neural Network Speech Separation Models2023 · 6 citesOn Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments2023 · 5 citesTF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation2022 · 3 citesExploring Self-Attention Mechanisms for Speech Separation2022 · 2 citesA two-stage speaker extraction algorithm under adverse acoustic conditions using a single-microphone2023 · 2 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 Separation2022LibriheavyMix: 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 fusion2024Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domain2021