Abstract
In order to develop computer tools for speech therapy that reliably classify speech productions, there is a need for speech production corpora that characterize the target population in terms of age, gender, and native language. Apart from including correct speech productions, in order to characterize the target population, the corpora should also include samples from people with speech sound disorders. In addition, the annotation of the data should include information on the correctness of the speech productions. Following these criteria, we collected a corpus that can be used to develop computer tools for speech and language therapy of Portuguese children with sigmatism. The proposed corpus contains European Portuguese children’s word productions in which the words have sibilant consonants. The corpus has productions from 356 children from 5 to 9 years of age. Some important characteristics of this corpus, that are relevant to speech and language therapy and computer science research, are that (1) the corpus includes data from children with speech sound disorders; and (2) the productions were annotated according to the criteria of speech and language pathologists, and have information about the speech production errors. These are relevant features for the development and assessment of speech processing tools for speech therapy of Portuguese children. In addition, as an illustration on how to use the corpus, we present three speech therapy games that use a convolutional neural network sibilants classifier trained with data from this corpus and a word recognition module trained on additional children data and calibrated and evaluated with the collected corpus.
Highlights
While most children learn how to speak in their native language and learn how to correctly produce the native language phonemes by the expected ages, for some children, the languageInformation 2020, 11, 470; doi:10.3390/info11100470 www.mdpi.com/journal/informationInformation 2020, 11, 470 acquisition process may be challenging [1]
We have shown that keyword spotting (KWS) is an adequate solution for similar speech therapy applications [12], since it permits dealing with unexpected speech effects, such as hesitations, doubts, repetitions, and other speech disturbing factors
It is worth noting that this result is achieved with absolutely no data from the BioVisualSpeech corpus used for acoustic model training, and, some performance degradation may be due to mismatch in acoustic characteristics
Summary
While most children learn how to speak in their native language and learn how to correctly produce the native language phonemes by the expected ages, for some children, the language. In order to develop the automatic speech processing modules for our serious games for sigmatism, we built a corpus of children’s speech that was previously proposed in Reference [11] This corpus contains isolated sibilants productions and productions of words with sibilants. One of the novelties of this work is that the data annotations include information on the quality of the sound productions according to SLPs criteria Another novelty is that the set of chosen words focuses on the EP sibilant consonants.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have