An FFT-Based Companding Front End for Noise-Robust Automatic Speech Recognition
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 suite...
Main Authors: | Bhiksha Raj, Lorenzo Turicchia, Bent Schmidt-Nielsen, Rahul Sarpeshkar |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2007-06-01
|
Series: | EURASIP Journal on Audio, Speech, and Music Processing |
Online Access: | http://dx.doi.org/10.1155/2007/65420 |
Similar Items
-
An FFT-Based Companding Front End for Noise-Robust Automatic Speech Recognition
by: Turicchia Lorenzo, et al.
Published: (2007-01-01) -
An FFT-Based Companding Front End for Noise-Robust Automatic Speech Recognition
by: Raj, Bhiksha, et al.
Published: (2011) -
Auditory Front-Ends for Noise-Robust Automatic Speech Recognition
by: Ja-Zang Yeh, et al.
Published: (2010) -
A speech locked loop for cochlear implants and speech prostheses
by: Wee, Keng Hoong, et al.
Published: (2012) -
An Articulatory Speech-Prosthesis System
by: Wee, Keng Hoong, et al.
Published: (2012)