A neural network-based text-dependent speaker verification system using suprasegmental features

Gómez, Ramón García; Barquilla, Ricardo López; Tera, José Ignacio Puertas; Bermudez, José Parera; Haton, Marie-Christine; Haton, Jean Paul; Alinat, Pierre; Moreno, Sofia; Hess, Wolfgang; Raya, Ma Araceli Sanchez; Gual, Eduardo Alberto Martínez; Daza, Juan Luis Navas-Chaveli; Christophe, Anne; Durel, Marie-Madeleine; Maugin, Genevieve; Hohmann, Silke

doi:10.21437/eurospeech.1999-256

Cited by 2 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This information is very useful in CASTT applications, which aim is to improve the quality of speech production and articulation, especially in cases when the vocalization is the main problem. Regarding to the development of CASTT, many European projects related to speech technology and speech therapy such as Orto Logo-Paedia [1], SPECO [2], ans ISAEUS [3] have been carried out during the last decade, some of them resulting in the development of software applications for speech therapy. However, there are no versions of these softwares available in Spanish, thus they cannot be used by speakers and speech therapists to train vocalization skills in Spanish.…”

Section: Introductionmentioning

confidence: 99%

Formant estimation in children²s speech and its application for a Spanish speech therapy tool

Rodríguez,

Lleida

2009

Speech and Language Technology in Education (SLaTE 2009)

View full text Add to dashboard Cite

This paper addresses the problem of how to estimate reliable formant frequencies in high-pitched speech (typical in children), and how to normalize these estimations, independent from vocal tract shape or length. The normalized formant frequencies are used to improve the performance of a Computer-Aided Speech Therapy Tool (CASTT) in Spanish. For this purpose, a study was conducted to see what is the relationship between child's height and their vocal tract length, using traditional technologies in speech processing like linear prediction LPC, homomorphic analysis and modeling of the vocal tract. Results of this study show a high correlation between child's height and their vocal tract length. The study is based on speech from 235 healthy children (110 females and 125 males) which contains Spanish vowels utterances, and enables calibration of a CASTT system for children with speech disorders.

show abstract

Section: Introductionmentioning

confidence: 99%