A neural net for blind separation of nonstationary signals

Matsuoka, Kiyotoshi; Ohya, Masahiro; Kawamoto, Mitsuru

doi:10.1016/0893-6080(94)00083-x

Cited by 253 publications

(122 citation statements)

References 8 publications

Supporting

Mentioning

119

Contrasting

Unclassified

Order By: Relevance

“…The non-stationarity was first taken into account by Matsuoka et al (1995). This problem has been studied by Parra and Spence (2000a) and Pham et al (2003).…”

Section: Accepted Manuscriptmentioning

confidence: 99%

Speech intelligibility improvement using convolutive blind source separation assisted by denoising algorithms

Kociński

2008

Speech Communication

View full text Add to dashboard Cite

“…The non-stationarity was first taken into account by Matsuoka et al (1995). This problem has been studied by Parra and Spence (2000a) and Pham et al (2003).…”

Section: Accepted Manuscriptmentioning

confidence: 99%

Speech intelligibility improvement using convolutive blind source separation assisted by denoising algorithms

Kociński

2008

Speech Communication

View full text Add to dashboard Cite

“…Ideally, each frequency component of the mixture signal contains an instantaneous mixture of the corresponding frequency components of the underlying source signals. One of the advantages of the frequency-domain BSS is that we can employ any ICA algorithm for instantaneous mixtures, such as the information maximization (Infomax) approach [19] combined with the natural gradient [20], Fast ICA [21], JADE [22], or an algorithm based on non-stationarity of signals [23]. If the frame size K is long enough to cover the main part of the impulse responses ij h , the convolutive model (2) can be approximated as an instantaneous model at each frequency [8,24]:…”

Section: Mixing Process and Convolutive Bssmentioning

confidence: 99%

Convolutive ICA for Audio Signals

Geravanchizadeh¹,

Hesam²

2012

Independent Component Analysis for Audio and Biosignal Applications

View full text Add to dashboard Cite

“…It was shown [20][21][22] that considering only simple statistics, such as decorrelation, it is possible to separate out the original signals. Moreover, such approach seems to be easier, computationally less consuming and more stable than methods using higher order statistics (HOS), which of-ten work satisfactorily in computer simulations while performing poorly for recordings in a real environment [21] and the results are somewhat unpredictable.…”

Section: Introductionmentioning

confidence: 99%

Convolutive Blind Signal Separation Spatial Effectiveness in Speech Intelligibility Improvement

2011

View full text Add to dashboard Cite

Blind signal separation is one of the latest methods to improve the signal to noise ratio. The main objective of blind source separation is the transformation of mixtures of recorded signals to obtain each source signal at the output of the procedure, assuming that they are statistically independent. For acoustic signals it can be concluded that the correct separation is possible only if the source signals are spatially separated. That finding suggests analogies with the classical spatial filtering (beamforming). In this study we analyzed an effect of the angular separation of two source signals (i.e. speech and babble noise) to improve speech intelligibility. For this purpose, we chose the blind source separation algorithm based on the convolutive separation, based on second order statistics only. As a system of sensors a dummy head was used (one microphone inside each ear canal), which simulated two hearing aids of a hearing impaired person. The speech reception threshold, before and after the blind source separation was determined. The results have shown significant improvement in speech intelligibility after applying blind source separation (speach reception threshold fell even more than a dozen dB) in cases where the source signals were angularly separated. However, in cases where the source signals were coming from the same directions, the improvement was not observed. Moreover, the effectiveness of the blind source separation, to a large extent, depended on the relative positions of signal sources in space.

show abstract

A neural net for blind separation of nonstationary signals

Cited by 253 publications

References 8 publications

Speech intelligibility improvement using convolutive blind source separation assisted by denoising algorithms

Speech intelligibility improvement using convolutive blind source separation assisted by denoising algorithms

Convolutive ICA for Audio Signals

Convolutive Blind Signal Separation Spatial Effectiveness in Speech Intelligibility Improvement

Contact Info

Product

Resources

About