Language Identification using Acoustic Models and Speaker Compensated Cepstral-Time Matrices

This work presents two contributions to language identification. The first contribution is the definition of a set of properly selected time-frequency features that are a valid alternative to the commonly used shifted delta cepstral features. As a second contribution, we show that significant perfor...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Castaldo, F., Dalmasso, E., Laface, P., Colibro, D., Vair, C.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Acoustic distortion Cepstral analysis cepstral-time matrices frame domain compensation language identification Loudspeakers Natural languages NIST Performance evaluation phonetic language models speaker and channel compensation Speech recognition Support vector machine classification Support vector machines Time frequency analysis
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!