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

Lukas Drude, Jens Heitkaemper, Christoph Boeddeker, Reinhold Haeb-Umbach
10/30/2019
cs.SDcs.CLeess.AS

Official code: fgnt/sms_wsj (135 stars, MIT, last commit 2024-06-07).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

fgnt/sms_wsjOfficial100%
MIT

SMS-WSJ: Spatialized Multi-Speaker Wall Street Journal database for multi-channel source separation and recognition

13528Shell, PythonOct 23, 20192 years agoMIT

Similar Papers

Joint speech and overlap detection: a benchmark over multiple audio setup and speech domains

82% match2023

ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding

82% match1 repo10.0k2022

VorTEX: Various overlap ratio for Target speech EXtraction

81% match2026

SAM Audio: Segment Anything in Audio

81% match2025

Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation

81% match1 repo2712024

Exploring the Integration of Speech Separation and Recognition with Self-Supervised Learning Representation

80% match2023

Cite this paper

@article{drude2019smswsj,
  title  = {SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition},
  author = {Lukas Drude and Jens Heitkaemper and Christoph Boeddeker and Reinhold Haeb-Umbach},
  year   = {2019},
  eprint = {1910.13934},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1910.13934}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1910.13934.svg)](https://codeofpaper.com/paper/1910.13934)

Discussion