標題: Single-channel speech enhancement in variable noise-level environment
作者: Lin, CT
電控工程研究所
Institute of Electrical and Control Engineering
關鍵字: filter bank;noise estimation;recurrent network;time-frequency analysis;word boundary detection
公開日期: 1-Jan-2003
摘要: This paper discusses the problem of single-channel speech enhancement in variable noise-level environment. Commonly used, single-channel subtractive-type speech enhancement algorithms always assume that the background noise level is fixed or slowly varying. In fact, the background noise level may vary quickly. This condition usually results in wrong speech/noise detection and wrong speech enhancement process. In order to solve this problem, we propose a new subtractive-type speech enhancement scheme in this paper. This new enhancement scheme uses the RTF (refined time-frequency parameter)-based RSONFIN (recurrent self-organizing neural fuzzy inference network) algorithm we developed previously to detect the word boundaries in the condition of variable background noise level. In addition, a new parameter (MiFre) is proposed to estimate the varying background noise level. Based on this parameter, the noise level information used for subtractive-type speech enhancement can be estimated not only during speech pauses, but also during speech segments. This new subtractive-type enhancement scheme has been tested and found to perform well, not only in variable background noise level condition, but also in fixed background noise level condition.
URI: http://dx.doi.org/10.1109/TSMCA.2003.811115
http://hdl.handle.net/11536/28214
ISSN: 1083-4427
DOI: 10.1109/TSMCA.2003.811115
期刊: IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART A-SYSTEMS AND HUMANS
Volume: 33
Issue: 1
起始頁: 137
結束頁: 144
Appears in Collections:Articles


Files in This Item:

  1. 000183600800013.pdf