Adaptive feature truncation to address acoustic mismatch in automatic recognition of children's speech

An algorithm for adaptive Mel frequency cepstral coefficients (MFCC) feature truncation is proposed to improve automatic speech recognition (ASR) performance under acoustically mismatched conditions. Using the relationship found between MFCC base feature truncation and degree of acoustic mismatch of...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:APSIPA transactions on signal and information processing 2016, Vol.5 (1)
Hauptverfasser: Ghai, Shweta, Sinha, Rohit
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!