Search | Korea Science

Park, Sun-Ho;Yoo, Ji-Ho;Choi, Seung-Jin
- Journal of KIISE:Software and Applications
- /
- v.36 no.3
- /
- pp.179-186
- /
- 2009
This paper proposes a target speech extraction which restores speech signal of a target speaker form noisy convolutive mixture of speech and an interference source. We assume that the target speaker is known and his/her utterances are available in the training time. Incorporating the additional information extracted from the training utterances into the separation, we combine convolutive blind source separation(CBSS) and non-negative decomposition techniques, e.g., probabilistic latent variable model. The nonnegative decomposition is used to learn a set of bases from the spectrogram of the training utterances, where the bases represent the spectral information corresponding to the target speaker. Based on the learned spectral bases, our method provides two postprocessing steps for CBSS. Channel selection step finds a desirable output channel from CBSS, which dominantly contains the target speech. Reconstruct step recovers the original spectrogram of the target speech from the selected output channel so that the remained interference source and background noise are suppressed. Experimental results show that our method substantially improves the separation results of CBSS and, as a result, successfully recovers the target speech.
PDF KSCI

Lee, Soo-Jeong;Shin, Kye-Hyeon;Kim, Soon-Hyob
- Journal of the Institute of Electronics Engineers of Korea SP
- /
- v.44 no.3
- /
- pp.97-104
- /
- 2007
Adaptive echo canceller(AEC) has become an important component in speech communication systems, including mobile phones and speech recognition. In these applications, the acoustic echo path has a long impulse response. We propose a moving-averge least mean square(MVLMS) algorithm with a detection method for acoustic echo cancellation. Using, the result of the tests that used colored input models clearly shows that the MVLMS detection algorithm has convergence performance superior to the least mean square(LMS) detection algorithm alone. Although the computational complexity of the new MVLMS algorithm is only slightly greater than that of the standard LMS detection algorithm, the new algorithm confers a significant improvement in stability.
PDF KSCI