@Article{SouzaSoNaSoMaMa:2018:InReNo,
author = "Souza, Francisco Carlos M. and Souza, Alinne C. Corr{\^e}a and
Nakamura, Gilberto M. and Soares, Marinalva Dias and Mandr{\'a},
Patr{\'{\i}}cia Pupin and Macedo, Alessandra A.",
affiliation = "{Universidade de S{\~a}o Paulo (USP)} and {Universidade de
S{\~a}o Paulo (USP)} and {Universidade de S{\~a}o Paulo (USP)}
and {Instituto Nacional de Pesquisas Espaciais (INPE)} and
{Universidade de S{\~a}o Paulo (USP)} and {Universidade de
S{\~a}o Paulo (USP)}",
title = "Investigating the recognition of non-articulatory sounds by using
statistical tests and support vector machine",
journal = "Advances in Intelligent Systems and Computing",
year = "2018",
volume = "738",
pages = "639--649",
keywords = "Delayed speech development · Speech recognition methods · Machine
learning · Automatic speech recognition.",
abstract = "People with articulation and phonological disorders need training
to plan and to execute sounds of speech. Compared to other
children, children with Down Syndrome have significantly delayed
speech development because they present developmental
disabilities, mainly apraxia of speech. In practice, speech
therapists plan and perform trainings of articulatory and
non-articulatory sounds such as blow production and popping lips
in order to assist speech production. Mobile applications can be
integrated into the clinical treatment to transcend the boundaries
of clinics and schedules and therefore reach more people at any
time. The use of artificial intelligence and machine learning
techniques can improve this kind of application. The aim of this
pilot study is to assess speech recognition methods prioritizing
the training of sounds for speech production, particularly the
non-articulatory sounds. These methods apply Mel-Frequency
Cepstrum Coefficients and Laplace transform to extract features,
as well as traditional statistical tests and Support Vector
Machine (SVM) to recognize sounds. This study also reports
experimental results regarding the effectiveness of the methods on
a set of 197 sounds. Overall, SVM provides higher accuracy.",
doi = "10.1007/978-3-319-77028-4_82",
url = "http://dx.doi.org/10.1007/978-3-319-77028-4_82",
issn = "2194-5357",
language = "en",
targetfile = "souza_investigating.pdf",
urlaccessdate = "28 abr. 2024"
}