講演抄録/キーワード |
講演名 |
2013-07-25 14:40
少数のステレオデータに基づく特徴量変換による残響除去 ○Aditya Arie Nugraha(豊橋技科大)・山本一公(豊田高専/豊橋技科大)・中川聖一(豊橋技科大) SP2013-54 |
抄録 |
(和) |
In this paper, we present a feature enhancement method that uses neural networks (NNs) to map the reverberant feature in a log-melspectral domain to its corresponding anechoic feature. The mapping is done by cascade NNs trained using Cascade2 algorithm with an implementation of segment-based normalization. Experiments using speaker identification (SID) and speech recognition (ASR) systems were conducted to evaluate the method. The experiments of SID system was conducted by using real noisy reverberant datasets, while CENSREC-4 evaluation framework was used as the evaluation for the ASR system. Using limited stereo data consisting of simultaneously recorded clean speech and reverberant speech, the proposed method could remarkably improve the performance of both systems. |
(英) |
In this paper, we present a feature enhancement method that uses neural networks (NNs) to map the reverberant feature in a log-melspectral domain to its corresponding anechoic feature. The mapping is done by cascade NNs trained using Cascade2 algorithm with an implementation of segment-based normalization. Experiments using speaker identification (SID) and speech recognition (ASR) systems were conducted to evaluate the method. The experiments of SID system was conducted by using real noisy reverberant datasets, while CENSREC-4 evaluation framework was used as the evaluation for the ASR system. Using limited stereo data consisting of simultaneously recorded clean speech and reverberant speech, the proposed method could remarkably improve the performance of both systems. |
キーワード |
(和) |
dereverberation / feature enhancement / cascade neural network / stereo data / speech recognition / speaker identification / / |
(英) |
dereverberation / feature enhancement / cascade neural network / stereo data / speech recognition / speaker identification / / |
文献情報 |
信学技報, vol. 113, no. 161, SP2013-54, pp. 7-12, 2013年7月. |
資料番号 |
SP2013-54 |
発行日 |
2013-07-18 (SP) |
ISSN |
Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
SP2013-54 |