Yayınlanmış 1 Ocak 2012
| Sürüm v1
Konferans bildirisi
Açık
CATALOG-BASED SINGLE-CHANNEL SPEECH-MUSIC SEPARATION WITH THE ITAKURA-SAITO DIVERGENCE
Oluşturanlar
- 1. TUBITAK BILGEM, Kocaeli, Turkey
- 2. Bogazici Univ, Comp Engn Dept, Istanbul, Turkey
- 3. Bogazici Univ, Elect & Elect Engn Dept, Istanbul, Turkey
Açıklama
In this study, we introduce a catalog-based single-channel speech-music separation method with the Itakura-Saito (IS) divergence measure. Previously, we have developed the catalog-based separation method with the Kullback-Leibler (KL)divergence. In the probabilistic point of view, IS divergence corresponds to a complex Gaussian observation models in speech-music separation task is carried out with both of catalog-based and traditional Non-Negative matrix Factorization (NMF) methods. The separation performance is compared using Speech-to-Music Ratio (SMR), Speech-to-Artifact Ratio (SAR) and speech recognition performance measure via the word Error Rate (WER). We showed that, using IS divergence in both of catalog-based or NMF based speech-music separation methods yields better separation performance than KL divergence. Moreover, in this study, it is shown that catalog-based approaches with both divergence measure outperform traditional NMF based approaches in speech recognition experiments.
Dosyalar
bib-8e8eb445-ac4e-42ab-97a4-eb27c0eee9fd.txt
Dosyalar
(209 Bytes)
| Ad | Boyut | Hepisini indir |
|---|---|---|
|
md5:602af51a9caa157ccc1a9a494a3ddddf
|
209 Bytes | Ön İzleme İndir |