Speech Enhancement Based on the Response Features of Facilitated EI Neurons
A real-time approach for the enhancement of speech at zero degree azimuth is proposed. This is achieved inspired by the response features of the “Facilitated EI neurons”. This way, frequency segregation through a bandpass filter bank is followed by “supression analysis” which inhibits sources that are not at “facilitated” positions. Unlike with the existing approaches for the solution of cocktail party problem, where the performance under low SNR (signal-to-noise ratio) reverberation conditions is severely limited, the proposed approach has the capability to circumvent these problems. This is quantified through both objective and subjective performance measures and supported by real world simulation examples.
KeywordsInferior Colliculus Blind Source Separation Speech Enhancement Reverberation Time Human Auditory System
Unable to display preview. Download preview PDF.
- 3.de Cheveigne, A.: The auditory system as a separation machine. In: Proceedings of International Symposium of Hearing (2000)Google Scholar
- 7.Virgag, N.: Single channel speech enhancement based on masking properties of the human auditory system. IEEE Transactions on Signal Processing 7, 126–137 (1999)Google Scholar
- 8.Barros, A.K., Rutkowski, T.M., Itakura, F., Ohnishi, N.: Estimation of speech embedded in a reverberant and noisy environment by independent component analysis and wavelets. IEEE Transactions on Neural Networks 13(4) (2002)Google Scholar
- 13.Hansen, J., Pellom, B.L.: An effective qualiy evaluation protocol for speech enhancement algorithms. In: Proceedings of ICSLP 1998, vol. 7, pp. 2819–2822 (1998)Google Scholar