Electronic Resource

MLSP 2007 Data Analysis Competition: Two-Stage Blind Source Separation Combining SIMO-Model-Based ICA and Binary Masking

التفاصيل البيبلوغرافية
العنوان: MLSP 2007 Data Analysis Competition: Two-Stage Blind Source Separation Combining SIMO-Model-Based ICA and Binary Masking
المؤلفون: Mori, Yoshimitsu, 12733, Osako, Keiichi, 12734, Miyabe, Shigeki, 12735, Takahashi, Yu, 12736, Saruwatari, Hiroshi, 12737, Shikano, Kiyohiro, 12738
بيانات النشر: IEEE 2007-08
نوع الوثيقة: Electronic Resource
مستخلص: This paper reviews a real-time two-stage blind source separation (BSS) method for convolutive mixtures of speech, in which a single-input multiple-output (SIMO)-model-based independent component analysis (ICA) and a SIMO-model-based binary masking are combined. SIMO-model-based ICA can separate the mixed signals, not into monaural source signals but into SIMO-model-based signals from independent sources in their original form at the microphones. Thus, the separated signals of SIMO-model-based ICA can maintain the spatial qualities of each sound source. Owing to this attractive property, SIMO-model-based binary masking can be applied to efficiently remove the residual interference components after SIMO-model-based ICA. In addition, the performance deterioration due to the latency problem in ICA can be mitigated by introducing real-time binary masking. We report the parameters used in MLSP 2007 data analysis, and the experimental evaluation of the proposed method's superiority to the conventional BSS methods, regarding static- and moving-sound separation.
conference paper
مصطلحات الفهرس: VoR
URL: https://naist.repo.nii.ac.jp/record/4796/files/MLSP_2007_51.pdf
https://doi.org/10.1109/MLSP.2007.4414281
9781424415656
https://doi.org/10.1109/MLSP.2007.4414281
الاتاحة: Open access content. Open access content
Copyright 2007 IEEE
open access
ملاحظة: application/pdf
English
Other Numbers: JANST oai:naist.repo.nii.ac.jp:00004796
51
56
1407001884
المصدر المساهم: NARA INST OF SCI & TECH
From OAIster®, provided by the OCLC Cooperative.
رقم الانضمام: edsoai.on1407001884
قاعدة البيانات: OAIster