Publication: Morphological processing of a dynamic compressive gammachirp filterbank for automatic speech recognition
Loading...
Identifiers
Publication date
2012
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Universidad Autonoma De Madrid. Escuela Politécnica Superior
Impact
Export
Abstract
The Dynamic Compressive Gammachirp is presented for producing auditory-inspired feature extraction in Automatic Speech Recognition. The proposed acoustic features combine spectral subtraction and two-dimensional non-linear filtering technique most usually employed for image processing: morphological filtering. These features have been proven to be more robust to noisy speech than those based on simpler auditory filterbanks like the classical mel-scaled triangular filterbank, the Gammatone filterbank and the passive Gammachirp in a noisy Isolet database.
Description
Actas de: VII Jornadas en Tecnología del Habla and III Iberian SLTECH Workshop (IberSPEECH 2012). Madrid, 21-23 noviembre 2012.
Keywords
Spectral subtraction, Morphological processing, Automatic speech recognition, Auditory-based features.
Bibliographic citation
Proceedings IberSPEECH 2012: VII Jornadas en Tecnología del Habla and III Iberian SLTech Workshop. (pp. 53-62). Madrid: Universidad Autónoma de Madrid. Escuela Politécnica Superior.