Automatic evaluation of characteristic speech disorders in children with cleft lip and palate

Abstract This paper discusses the automatic evaluation of speech of chil-dren with cleft lip and palate (CLP). CLP speech shows specialcharacteristics such as hypernasality, backing, and weakeningof plosives. In total ve criteria were subjectively assessed byan experienced speech expert on the phone level. This subjec-tive evaluation was used as a gold standard to train a classi-cation system. The automatic system achieves recognition re-sults on frame, phone, and word level of up to 75.8% CL. Onspeaker level signicant and high correlations between the sub-jective evaluation and the automatic system of up to 0.89 areobtained. Index Terms : pathologic speech, speech assessment, pronun-ciation scoring, children’s speech 1. Introduction Cleft Lip and Palate (CLP) is the most common malformationof the head. It constitutes almost two-thirds of the major facialdefects and almost 80% of all orofacial clefts [1]. Its prevalencediffers in different populations from 1 in 400 to 500 newborns inAsians to 1 in 1500 to 2000 in African Americans. The preva-lence in Caucasians is 1 in 750 to 900 births [2, 3].In clinical practice, articulation disorders are mainly eval-uated by subjective tools. The simplest method is the audi-tive perception, mostly performed by a speech therapist. Pre-vious studies have shown that experience is an important fac-tor that inuences the subjective estimation of speech disorderswhich leads to inaccurate evaluation by persons with only fewyears of experience as speech therapist [4]. Until now, objectivemeans exist only for quantitative measurements of nasal emis-sions [5, 6, 7] and for the detection of secondary voice disorders[8]. But other specic articulation disorders in CLP cannot besufciently quantied.In this paper, we present a new technical procedure for themeasurement and evaluation of specic speech disorders andcompare the results obtained with subjective ratings of an expe-rienced speech therapist.

[1]  Helmer Strik,et al.  Feedback in computer assisted pronunciation training: technology push or demand pull? , 2002, INTERSPEECH.

[2]  Elmar Nöth,et al.  Pronunciation Feature Extraction , 2005, DAGM-Symposium.

[3]  J J Murray,et al.  Cleft lip and palate care in the United Kingdom--the Clinical Standards Advisory Group (CSAG) Study. Part 3: speech outcomes. , 2001, The Cleft palate-craniofacial journal : official publication of the American Cleft Palate-Craniofacial Association.

[4]  M H Moore,et al.  Rare Craniofacial Clefts , 1996, The Journal of craniofacial surgery.

[5]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[6]  R. Sader,et al.  Perzeptive und apparative Untersuchung der Stimmqualität bei Patienten mit Lippen-Kiefer-Gaumenspalten , 1998 .

[7]  Tino Haderlein,et al.  Evaluation of Tracheoesophageal Substitute Voices Using Prosodic Features , 2006 .

[8]  Elmar Nöth,et al.  Intelligibility of Children with Cleft Lip and Palate: Evaluation by Speech Recognition Techniques , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[9]  R. Wyatt,et al.  Speech after repair of isolated cleft palate and cleft lip and palate. , 2001, British journal of plastic surgery.

[10]  Wayne Ozaki,et al.  Rare Craniofacial Clefts , 2004 .

[11]  P. Dejonckere,et al.  Objectivating nasality in healthy and velopharyngeal insufficient children with the Nasalance Acquisition System (NasalView). Defining minimal required speech tasks assessing normative values for Dutch language. , 2004, International journal of pediatric otorhinolaryngology.

[12]  K. Pearson.  Mathematical Contributions to the Theory of Evolution. III. Regression, Heredity, and Panmixia , 1896 .

[13]  J. Červenka,et al.  Classification and birth prevalence of orofacial clefts. , 1998, American journal of medical genetics.

[14]  Ian Witten,et al.  Data Mining , 2000 .

[15]  John A van Aalst,et al.  The spectrum of orofacial clefting. , 2005, Plastic and reconstructive surgery.

[16]  Marc De Bodt,et al.  Outcome of Treatment regarding Articulation, Resonance and Voice in Flemish Adults with Unilateral and Bilateral Cleft Palate , 2003, Folia Phoniatrica et Logopaedica.

[17]  Elmar Nöth,et al.  Visualization of Voice Disorders Using the Sammon Transform , 2006, TSD.

[18]  P. Van cauwenberge,et al.  Effect of Cleft Type on Overall Speech Intelligibility and Resonance , 2002, Folia Phoniatrica et Logopaedica.

[19]  J.H.L. Hansen,et al.  A noninvasive technique for detecting hypernasal speech using a nonlinear operator , 1996, IEEE Transactions on Biomedical Engineering.

[20]  Elmar Nöth,et al.  Boosting of Prosodic and Pronunciation Features to Detect Mispronunciations of Non-Native Children , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[21]  M. Ptok,et al.  Objektive Messung der Nasalanz in der deutschen Hochlautung , 2003, HNO.

[22]  Stan Davis,et al.  Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Se , 1980 .

[23]  Georg Stemmer.  Modeling variability in speech recognition , 2004 .

[24]  M Ptok,et al.  [Normal nasalance for the German language. Nasometric values for clinical use in patients with cleft lip and palate]. , 2003, HNO.