Title :
Cepstrum-based deconvolution for speech dereverberation
Author :
Subramaniam, Suresh ; Petropulu, Athina P. ; Wendt, Christopher
Author_Institution :
Dept. of Electr. & Comput. Eng., Drexel Univ., Philadelphia, PA, USA
fDate :
9/1/1996 12:00:00 AM
Abstract :
We present a blind deconvolution-based approach for the restoration of speech degraded by the acoustic environment. The proposed scheme processes the outputs of two microphones using cepstra operations and the theory of signal reconstruction from phase only. Under mild assumptions, it reconstructs the room impulse response associated with each microphone and restores the speech signal
Keywords :
acoustic signal processing; architectural acoustics; cepstral analysis; deconvolution; microphones; reverberation; signal reconstruction; speech processing; transient analysis; transient response; acoustic environment; blind deconvolution; cepstra operations; cepstrum based deconvolution; degraded speech restoration; microphones; phase; room impulse response; signal reconstruction; speech dereverberation; speech signal; Acoustic signal processing; Deconvolution; Degradation; Hidden Markov models; Microphones; Natural languages; Signal restoration; Speech processing; Speech recognition; Training data;
Journal_Title :
Speech and Audio Processing, IEEE Transactions on
