An FFT-Based Companding Front End for Noise-Robust Automatic Speech Recognition

An FFT-Based Companding Front End for Noise-Robust Automatic Speech Recognition

Show other versions (1)

We describe an FFT-based companding algorithm for preprocessing speech before recognition. The algorithm mimics tone-to-tone suppression and masking in the auditory system to improve automatic speech recognition performance in noise. Moreover, it is also very computationally efficient and suited to...

Full description

Bibliographic Details
Main Authors: Raj, Bhiksha (Author), Turicchia, Lorenzo (Contributor), Schmidt-Nielsen, Bent (Author), Sarpeshkar, Rahul (Contributor)
Other Authors: Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor), Massachusetts Institute of Technology. Research Laboratory of Electronics (Contributor)
Format: Article
Language:English
Published: Hindawi Publishing Corporation, 2011-11-16T13:45:46Z.
Subjects:
Article
Online Access:Get fulltext

Internet

Get fulltext

Similar Items