Abstract
The automatic evaluation of reading performance of children is an important alternative to any manual or 1-on-1 evaluation by teachers or tutors. To do this, it is necessary to detect several types of reading miscues. This work presents an approach to annotate reading speech while detecting false-starts, repetitions and mispronunciations, three of the most common disfluencies. Using speech data of 6–10 year old children reading sentences and pseudowords, we apply a two-step process: first, an automatic alignment is performed to get the best possible word-level segmentation and detect syllable based false-starts and word repetitions by using a strict FST (Finite State Transducer); then, words are classified as being mispronounced or not through a likelihood measure of pronunciation by using phone posterior probabilities estimated by a neural network. This work advances towards getting the amount and severity of disfluencies to provide a reading ability score computed from several sentence reading tasks.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
National Reading Panel: Teaching children to read: an evidence-based assessment of the scientific research literature on reading and its implications for reading instruction. National Institute of Child Health and Human Development (2000)
Abdou, S.M., Hamid, S.E., Rashwan, M., Samir, A., Abdel-Hamid, O., Shahin, M., Nazih, W.: Computer aided pronunciation learning system using speech recognition techniques. In: INTERSPEECH (2006)
Cincarek, T., Gruhn, R., Hacker, C., Nöth, E., Nakamura, S.: Automatic pronunciation scoring of words and sentences independent from the non-native’s first language. Comput. Speech Lang. 23(1), 65–88 (2009)
Mostow, J., Roth, S.F., Hauptmann, A.G., Kane, M.: A prototype reading coach that listens. In: Proceedings of 12th National Conference on Artificial Intelligence, vol. 1, Menlo Park, pp. 785–792 (1994)
Black, M., Tepperman, J., Lee, S., Price, P., Narayanan, S.: Automatic detection and classification of disfluent reading miscues in young children’s speech for the purpose of assessment. Presented at the Proceedings of Interspeech, pp. 206–209 (2007)
Duchateau, J., Kong, Y.O., Cleuren, L., Latacz, L., Roelens, J., Samir, A., Demuynck, K., Ghesquière, P., Verhelst, W., Hamme, H.V.: Developing a reading tutor: design and evaluation of dedicated speech recognition and synthesis modules. Speech Commun. 51(10), 985–994 (2009)
Bolaños, D., Cole, R.A., Ward, W., Borts, E., Svirsky, E.: FLORA: fluent oral reading assessment of children’s speech. ACM Trans. Speech Lang. Process. 7(4), 16:1–16:19 (2011)
The LetsRead Project - Automatic assessment of reading ability of children. http://lsi.co.it.pt/spl/projects_letsread.html. Accessed 25 Mar 2016
Candeias, S., Celorico, D., Proença, J., Veiga, A., Perdigão, F.: HESITA(tions) in Portuguese: a database. In: ISCA, Interspeech Satellite Workshop on Disfluency in Spontaneous Speech - DiSS, pp. 13–16. KTH Royal Institute of Technology, Stockholm (2013)
Liu, Y., Shriberg, E., Stolcke, A., Harper, M.P.: Comparing HMM, maximum entropy, and conditional random fields for disfluency detection. In: Proceedings of Interspeech, pp. 3313–3316 (2005)
Medeiros, H., Moniz, H., Batista, F., Trancoso, I., Nunes, L., et al.: Disfluency detection based on prosodic features for university lectures. In: Proceedings of Interspeech, Lyon, France, pp. 2629–2633 (2013)
Moniz, H., Batista, F., Mata, A.I., Trancoso, I.: Speaking style effects in the production of disfluencies. Speech Commun. 65, 20–35 (2014)
Duchateau, J., Cleuren, L., Hamme, H.V., Ghesquière, P.: Automatic assessment of children’s reading level. In: Proceedings of Interspeech, Antwerp, Belgium, pp. 1210–1213 (2007)
Yilmaz, E., Pelemans, J., Hamme, H.V.: Automatic assessment of children’s reading with the FLaVoR decoding using a phone confusion model. In: Proceedings of Interspeech, Singapore, pp. 969–972 (2014)
Li, X., Ju, Y.-C., Deng, L., Acero, A.: Efficient and robust language modeling in an automatic children’s reading tutor system. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 4, pp. 193–196 (2007)
Proença, J., Celorico, D., Candeias, S., Lopes, C., Perdigão, F., Children’s reading aloud performance: a database and automatic detection of disfluencies. In: ISCA - Conference of the International Speech Communication Association - INTERSPEECH, Dresden, Germany, pp. 1655–1659 (2015)
Black, M.P., Tepperman, J., Narayanan, S.S.: Automatic prediction of children’s reading ability for high-level literacy assessment. Trans. Audio Speech and Lang. Process. 19(4), 1015–1028 (2011)
Proenca, J., Celorico, D., Candeias, S., Lopes, C., Perdigão, F.: The LetsRead corpus of portuguese children reading aloud for performance evaluation. In: Proceedings of 10th Edition of the Language Resources and Evaluation Conference (LREC 2016), Portorož, Slovenia (2016)
Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motlicek, P., Qian, Y., Schwarz, P., Silovsky, J., Stemmer, G., Vesely, K.: The Kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding, Hilton Waikoloa Village, Big Island, Hawaii, US (2011)
Phoneme recognizer based on long temporal context. Brno University of Technology, FIT. http://speech.fit.vutbr.cz/software/phoneme-recognizer-based-long-temporal-context. Accessed 06 May 2015
Veiga, A., Lopes, C., Sá, L., Perdigão, F.: Acoustic similarity scores for keyword spotting. In: Baptista, J., Mamede, N., Candeias, S., Paraboni, I., Pardo, Thiago, A.,S., Volpe Nunes, M.d.G (eds.) PROPOR 2014. LNCS (LNAI), vol. 8775, pp. 48–58. Springer, Heidelberg (2014). doi:10.1007/978-3-319-09761-9_5
Fiscus, J.G., Ajot, J., Garofolo, J.S., Doddingtion, G.: Results of the 2006 spoken term detection evaluation. In: Proceedings of SIGIR, vol. 7, pp. 51–57 (2007)
Acknowledgements
This work was supported in part by Fundação para a Ciência e Tecnologia under the project UID/EEA/50008/2013 (pluriannual funding in the scope of the LETSREAD project). Jorge Proença is supported by the SFRH/BD/97204/2013 FCT Grant. We would like to thank João de Deus, Bissaya Barreto and EBI de Pereira school associations and CASPAE parent’s association for collaborating in the database collection.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Proença, J., Celorico, D., Lopes, C., Candeias, S., Perdigão, F. (2016). Automatic Annotation of Disfluent Speech in Children’s Reading Tasks. In: Abad, A., et al. Advances in Speech and Language Technologies for Iberian Languages. IberSPEECH 2016. Lecture Notes in Computer Science(), vol 10077. Springer, Cham. https://doi.org/10.1007/978-3-319-49169-1_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-49169-1_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-49168-4
Online ISBN: 978-3-319-49169-1
eBook Packages: Computer ScienceComputer Science (R0)