کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
7116697 1461208 2017 8 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Speaker conversion using kernel non-negative matrix factorization
ترجمه فارسی عنوان
تبدیل بلندگو با استفاده از تقسیم ماتریس غیر منفی هسته
کلمات کلیدی
موضوعات مرتبط
مهندسی و علوم پایه سایر رشته های مهندسی مهندسی برق و الکترونیک
چکیده انگلیسی
Voice conversion (VC) based on Gaussian mixture model (GMM) is the most classic and common method which converts the source spectrum to target spectrum. However this method is prone to over-fitting because of its frame-by-frame conversion. The VC with non-negative matrix factorization (NMF) is presented in this paper, which can keep spectrum from over-fitting by adjusting the size of basis vector (dictionary). In order to realize the non-linear mapping better, kernel NMF (KNMF) is adopted to achieve spectrum mapping. In addition, to increase the accuracy of conversion, KNMF combined with GMM (GKNMF) is also introduced into VC. In the end, KNMF, GKNMF, GMM, principal component regression (PCR), PCR combined with GMM (GPCR), partial least square regression (PLSR), NMF correlation-based frequency warping (NMF-CFW) and deep neural network (DNN) methods are compared with each other. The proposed GKNMF gets better performance in both objective evaluation and subjective evaluation.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: The Journal of China Universities of Posts and Telecommunications - Volume 24, Issue 5, October 2017, Pages 60-67
نویسندگان
, , , , ,