WHAMR!: Noisy and Reverberant Single-Channel Speech Separation
This addresses the challenge of realistic speech separation for applications in noisy indoor environments, but it is incremental as it extends an existing dataset and benchmarks current techniques.
The paper tackled the problem of single-channel speech separation in noisy and reverberant conditions, which degrade standard systems, by introducing the WHAMR! dataset with synthetic reverberation and providing baseline analyses, showing performance degradation in existing methods.
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.