论文信息 - On amplitude modulation for monaural speech segregation

On amplitude modulation for monaural speech segregation

We propose a computational auditory scene analysis (CASA) model for monaural speech segregation. It deals with low-frequency and high-frequency signals differently. For high-frequency signals, it generates segments based on the common amplitude modulation (AM) and groups them according to AM repetition rates. This model performs substantially better than previous CASA systems.

DeLiang Wang | Guoning Hu | Deliang Wang | G. Hu

[1] E. Owens,et al. An Introduction to the Psychology of Hearing , 1997 .

[2] C. J. Darwin,et al. Chapter 11 – Auditory Grouping , 1995 .

[3] Phil D. Green,et al. Robust automatic speech recognition with missing and unreliable acoustic data , 2001, Speech Commun..

[4] Guy J. Brown,et al. Computational auditory scene analysis , 1994, Comput. Speech Lang..

[5] Ernst Mach,et al. Sensations of tone. , 1897 .

[6] R. Kumaresan,et al. Model-based approach to envelope and positive instantaneous frequency estimation of signals with speech applications , 1999 .

[7] B. Moore. An Introduction to the Psychology of Hearing , 1977 .

[8] Guy J. Brown,et al. Separation of speech from interfering sounds based on oscillatory correlation , 1999, IEEE Trans. Neural Networks.

[9] Hermann von Helmholtz,et al. On the Sensations of Tone , 1954 .

[10] Asoke K. Nandi,et al. Blind Source Separation , 1999 .

[11] David F. Rosenthal,et al. Computational auditory scene analysis , 1998 .