SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition

• DOI: 10.48550/arxiv.1910.13934
• Publication Date: 2019-01-01
• Authors: Drude, Lukas; Heitkaemper, Jens; Boeddeker, Christoph; Haeb-Umbach, Rein...
• Keywords: FOS: Computer and information sciences; 03 medical and health sciences; Sound (cs.SD); Computer Science - Computation and Language; Audio and Speech Processing (eess.AS); FOS: Electrical engineering, electronic engineering, information engineering; 0305 other medical science; Computation and Language (cs.CL); Computer Science - Sound; Electrical Engineering and Systems Science - Audio and Speech Processing

Submitted to ICASSP 2020<br/>We present a multi-channel database of overlapping speech for training, evaluation, and detailed analysis of source separation and extraction algorithms: SMS-WSJ -- Spatialized Multi-Speaker Wall Street Journal. It consists of artificially mixed speech taken from the WSJ database, but unlike earlier databases we consider all WSJ0+1 utterances and take care of strictly separating the speaker sets present in the training, validation and test sets. When spatializing the data we ensure a high degree of randomness w.r.t. room size, array center and rotation, as well as speaker position. Furthermore, this paper offers a critical assessment of recently proposed measures of source separation performance. Alongside the code to generate the database we provide a source separation baseline and a Kaldi recipe with competitive word error rates to provide common ground for evaluation.<br/>