ゼミナール発表

日時: 9月24日(火)3限 (13:30 - 15:00)


会場: L1

司会: Kevin Duh
宮�� 亮一 1261017: D, 中間発表 中村 哲, 杉本 謙二, 猿渡洋
title: Musical-Noise-Free Blind Speech Extraction using ICA-Based Noise Estimation and Iterative Spectral Subtraction
abstract: In our previous study, it was found that optimized iterative spectral subtraction (SS) results in speech enhancement with almost no musical noise generation, but this method is valid only for stationary noise. The proposed method consists of iterative blind dynamic noise estimation by independent component analysis (ICA) and musical-noise-free speech extraction by modified iterative SS, where multiple iterative SS is applied to each channel while maintaining the multi-channel property reused for ICA. Also, related to the proposed method, we discuss the justification of applying ICA to such signals nonlinearly distorted by SS. From objective and subjective evaluations, we reveal that the proposed method outperforms the conventional method.
language of the presentation: Japanese
 
松宮 翔 1251097: M, 2回目発表 中村 哲, 松本 裕治, 戸田智基, Sakriani Sakti, Graham Neubig
 
水上 雅博 1251101: M, 2回目発表 中村 哲, 松本 裕治, 戸田智基, Graham Neubig, Sakriani Sakti
 
丹生 伊左夫 1251079: M, 2回目発表 中村 哲, 松本 裕治, 戸田智基, Graham Neubig, Sakriani Sakti