TY - GEN
T1 - Amplitude-based speech enhancement with nonnegative matrix factorization for asynchronous distributed recording
AU - Chiba, Hironobu
AU - Ono, Nobutaka
AU - Miyabe, Shigeki
AU - Takahashi, Yu
AU - Yamada, Takeshi
AU - Makino, Shoji
N1 - Funding Information:
This work was supported by a Grant-in-Aid for Scientific Research (B) (Japan Society for the Promotion of Science (JSPS) KAKENHI Grant Number 25280069).
Publisher Copyright:
© 2014 IEEE.
PY - 2014/11/11
Y1 - 2014/11/11
N2 - In this paper, we investigate amplitude-based speech enhancement for asynchronous distributed recording. In an ad-hoc microphone array context, it is supposed that different asynchronous devices record speech. As a result, the phase information is unreliable due to sampling frequency mismatch. For speech enhancement based on the amplitude information instead of the phase information, supervised nonnegative matrix factorization (NMF) is introduced in the time-channel domain. The basis vectors, which represents the gain of the transfer function from a source to each microphone, are trained in advance by using single source observation. The experimental evaluations show that this approach is well robust against the sampling frequency mismatch.
AB - In this paper, we investigate amplitude-based speech enhancement for asynchronous distributed recording. In an ad-hoc microphone array context, it is supposed that different asynchronous devices record speech. As a result, the phase information is unreliable due to sampling frequency mismatch. For speech enhancement based on the amplitude information instead of the phase information, supervised nonnegative matrix factorization (NMF) is introduced in the time-channel domain. The basis vectors, which represents the gain of the transfer function from a source to each microphone, are trained in advance by using single source observation. The experimental evaluations show that this approach is well robust against the sampling frequency mismatch.
KW - ad-hoc microphone array
KW - nonnegative matrix fac-torization
KW - sampling frequency mismatch
KW - Speech enhancement
KW - time-frequency masking
UR - http://www.scopus.com/inward/record.url?scp=84957635192&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84957635192&partnerID=8YFLogxK
U2 - 10.1109/IWAENC.2014.6954007
DO - 10.1109/IWAENC.2014.6954007
M3 - Conference contribution
AN - SCOPUS:84957635192
T3 - 2014 14th International Workshop on Acoustic Signal Enhancement, IWAENC 2014
SP - 203
EP - 207
BT - 2014 14th International Workshop on Acoustic Signal Enhancement, IWAENC 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 14th International Workshop on Acoustic Signal Enhancement, IWAENC 2014
Y2 - 8 September 2014 through 11 September 2014
ER -