http://www.cnr.it/ontology/cnr/individuo/prodotto/ID179448

On the Development of Matched and Mismatched Italian Children's Speech Recognition Systems (Contributo in atti di convegno)

Type

Prodotto della ricerca (Classe)
Contributo in atti di convegno (Classe)

Label

On the Development of Matched and Mismatched Italian Children's Speech Recognition Systems (Contributo in atti di convegno) (literal)

Anno

2009-01-01T00:00:00+01:00 (literal)

Alternative label

Cosi P; (2009)
On the Development of Matched and Mismatched Italian Children's Speech Recognition Systems
in INTERSPEECH 2009, Brighton, UK, 6-10 Settembre 2009
(literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori

Cosi P; (literal)

Pagina inizio

540 (literal)

Pagina fine

543 (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#altreInformazioni

CD Proceedings ISSN: 1990-9772 Printed Proceedings IDS Number: BOJ53 ISBN: 978-1-61567-692-7 ISI Web of Science On the Development of Matched and Mismatched Italian Children's Speech Recognition Systems Author(s): Cosi, P (Cosi, Piero) Book Group Author(s): ISCA-INST SPEECH COMMUN ASSOC Source: INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5 Pages: 576-579 Published: 2009 Times Cited: 0 (from Web of Science) Cited References: 16 [ view related records ] Citation MapCitation Map Conference: 10th INTERSPEECH 2009 Conference Location: Brighton, ENGLAND Date: SEP 06-10, 2009 Sponsor(s): Int Speech Commun Assoc Abstract: While at least read speech corpora are available for Italian children's speech research, there exist many languages which completely lack children's speech corpora. We propose that learning statistical mappings between the adult and child acoustic space using existing adult/children corpora may provide a future direction for generating children's models for such data deficient languages. In this work the recent advances in the development of the SONIC Italian children's speech recognition system will be described. This work, completing a previous one developed in the past, was conducted with the specific goals of integrating the newly trained children's speech recognition models into the Italian version of the Colorado Literacy Tutor platform. Specifically, children's speech recognition research for Italian was conducted using the complete training and test set of the FBK (ex ITC-irst) Italian Children's Speech Corpus (Child It). Using the University of Colorado SONIC LVSR system, we demonstrate a phonetic recognition error rate of 12,0% for a system which incorporates Vocal Tract Length Normalization (VTLN), Speaker-Adaptive Trained phonetic models, as well as unsupervised Structural MAP Linear Regression (SMAPLR). Accession Number: WOS:000276842800142 Document Type: Proceedings Paper Language: English Author Keywords: children; ASR; Italian; adaptation Reprint Address: Cosi, P (reprint author), CNR, Ist Sci & Tecnol Cogniz, I-00185 Rome, Italy Addresses: 1. CNR, Ist Sci & Tecnol Cogniz, I-00185 Rome, Italy E-mail Address: piero.cosi@pd.istc.cnr.it Publisher: ISCA-INST SPEECH COMMUNICATION ASSOC, C/O EMMANUELLE FOXONET, 4 RUE DES FAUVETTES, LIEU DIT LOUS TOURILS, BAIXAS, F-66390, FRANCE Web of Science Category: Computer Science, Artificial Intelligence; Engineering, Electrical & Electronic Subject Category: Computer Science; Engineering IDS Number: BOJ53 ISBN: 978-1-61567-692-7 (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#url

http://www.isca-speech.org/archive/interspeech_2009/ (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#titoloVolume

10th Annual Conference of the International Speech Communication Association (INTERSPEECH 2009) (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#volumeInCollana

4 (2009) (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#pagineTotali

4 (literal)

Note

ISI Web of Science (WOS) (literal)
Scopu (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni

Istituto di Scienze e Tecnologie della Cognizione, C.N.R. (literal)

Titolo

On the Development of Matched and Mismatched Italian Children's Speech Recognition Systems (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#isbn

978-1-61567-692-7 (literal)

Abstract

While at least read speech corpora are available for Italian children's speech research, there exist many languages which completely lack children's speech corpora. We propose that learning statistical mappings between the adult and child acoustic space using existing adult/children corpora may provide a future direction for generating children's models for such data deficient languages. In this work the recent advances in the development of the SONIC Italian children's speech recognition system will be described. This work, completing a previous one developed in the past, was conducted with the specific goals of integrating the newly trained children's speech recognition models into the Italian version of the Colorado Literacy Tutor platform. Specifically, children's speech recognition research for Italian was conducted using the complete training and test set of the FBK (ex ITC-irst) Italian Children's Speech Corpus (ChildIt). Using the University of Colorado SONIC LVSR system, we demonstrate a phonetic recognition error rate of 12,0% for a system which incorporates Vocal Tract Length Normalization (VTLN), Speaker-Adaptive Trained phonetic models, as well as unsupervised Structural MAP Linear Regression (SMAPLR). (literal)

Editore