WHAMR!: Noisy And Reverberant Single-channel Speech Separation

Abstract

While significant advances have been made with respect to the separation of overlapping speech signals, studies have been largely constrained to mixtures of clean, near anechoic speech, not representative of many real-world scenarios. Although the WHAM! dataset introduced noise to the ubiquitous wsj0-2mix dataset, it did not include reverberation, which is generally present in indoor recordings outside of recording studios. The spectral smearing caused by reverberation can result in significant performance degradation for standard deep learning-based speech separation systems, which rely on spectral structure and the sparsity of speech signals to tease apart sources. To address this, we introduce WHAMR!, an augmented version of WHAM! with synthetic reverberated sources, and provide a thorough baseline analysis of current techniques as well as novel cascaded architectures on the newly introduced conditions.

Stats

• citations139
• S2 citations—
• github stars0
• HF likes0
• heat score16.10
• arxiv keymaciejewski2019whamr

Related papers

• Libriheavymix: A 20,000-hour Dataset For Single-channel Reverberant Multi-talker Speech Separation, ASR And Speaker Diarization (2024)5.24
• Monaural Source Separation: From Anechoic To Reverberant Environments (2021)10.61
• A Two-stage Speaker Extraction Algorithm Under Adverse Acoustic Conditions Using A Single-microphone (2023)0.00
• End-to-end Dereverberation, Beamforming, And Speech Recognition With Improved Numerical Stability And Advanced Frontend (2021)10.97
• Exploring The Integration Of Speech Separation And Recognition With Self-supervised Learning Representation (2023)6.34
• Time-domain Speech Extraction With Spatial Information And Multi Speaker Conditioning Mechanism (2021)7.81
• Short-time Deep-learning Based Source Separation For Speech Enhancement In Reverberant Environments With Beamforming (2020)0.00
• SMS-WSJ: Database, Performance Measures, And Baseline Recipe For Multi-channel Source Separation And Recognition (2019)0.00