We propose a novel universal acoustic characterization approach to spoken language identification (LID), in which any spoken language is described with a common set of fundamental units defined “universally.” Specifically, manner and place of articulation form this unit inventory and are used to build a set of universal attribute models with data-driven techniques. Using the vector space modeling approaches to LID a spoken utterance is first decoded into a sequence of attributes. Then, a feature vector consisting of co-occurrence statistics of attribute units is created, and the final LID decision is implemented with a set of vector space language classifiers. Although the present study is just in its preliminary stage, promising results comparable to acoustically rich phone-based LID systems have already been obtained on the NIST 2003 LID task. The results provide clear insight for further performance improvements and encourage a continuing exploration of the proposed framework.
S. M. SINISCALCHI, J. REED, T. SVENDSEN, AND C.-H. LEE (2009). Exploring Universal Attribute Characterization of Spoken Languages for Spoken Language Recognition. In INTERSPEECH 2009 (pp. 168-171). ISCA-INST SPEECH COMMUNICATION ASSOC, C/O EMMANUELLE FOXONET, 4 RUE DES FAUVETTES, LIEU DIT LOUS TOURILS [10.21437/Interspeech.2009-67].
Exploring Universal Attribute Characterization of Spoken Languages for Spoken Language Recognition
S. M. SINISCALCHI;
2009-01-01
Abstract
We propose a novel universal acoustic characterization approach to spoken language identification (LID), in which any spoken language is described with a common set of fundamental units defined “universally.” Specifically, manner and place of articulation form this unit inventory and are used to build a set of universal attribute models with data-driven techniques. Using the vector space modeling approaches to LID a spoken utterance is first decoded into a sequence of attributes. Then, a feature vector consisting of co-occurrence statistics of attribute units is created, and the final LID decision is implemented with a set of vector space language classifiers. Although the present study is just in its preliminary stage, promising results comparable to acoustically rich phone-based LID systems have already been obtained on the NIST 2003 LID task. The results provide clear insight for further performance improvements and encourage a continuing exploration of the proposed framework.File | Dimensione | Formato | |
---|---|---|---|
INTERSPEECH_2009.pdf
Solo gestori archvio
Descrizione: Il testo pieno dell’articolo è disponibile al seguente link: https://www.isca-archive.org/interspeech_2009/siniscalchi09_interspeech.pdf
Tipologia:
Versione Editoriale
Dimensione
239.95 kB
Formato
Adobe PDF
|
239.95 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.