Artificial neural network analysis to assess hypernasality in patients treated for oral or oropharyngeal cancer

Abstract Objective. Investigation of applicability of neural network feature analysis of nasalance in speech to assess hypernasality in speech of patients treated for oral or oropharyngeal cancer. Patients and methods. Speech recordings of 51 patients and of 18 control speakers were evaluated regarding hypernasality, articulation, intelligibility, and patient-reported speech outcome. Feature analysis of nasalance was performed on /a/, /i/, and /u/ and on the entire stretch of speech. Results. Nasalance distinguished significantly between patients and controls. Nasalance in /a/ and /i/ predicted best intelligibility, nasalance in /a/ predicted best articulation, and nasalance in /i/ and /u/ predicted best hypernasality. Conclusion. Feature analysis of nasalance in oral or oropharyngeal cancer patients is feasible; prediction of subjective parameters varies between moderate and poor.

[1]  Simon King,et al.  Detection of phonological features in continuous speech using neural networks , 2000, Comput. Speech Lang..

[2]  P. Fayers,et al.  Quality of life in head and neck cancer patients: validation of the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire-H&N35. , 1999, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[3]  Johannes A Langendijk,et al.  Speech outcome after surgical treatment for oral and oropharyngeal cancer: A longitudinal assessment of patients reconstructed by a microvascular flap , 2005, Head & neck.

[4]  Carol Y. Espy-Wilson,et al.  Knowledge-based parameters for HMM speech recognition , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[5]  K Shimodaira,et al.  Spectral characteristics of hypernasality in maxillectomy patients. , 2000, Journal of oral rehabilitation.

[6]  Britta Hammarberg,et al.  The pharyngoesophageal segment in laryngectomees—videoradiographic, acoustic, and voice quality perceptual data , 2008, Logopedics, phoniatrics, vocology.

[7]  George H. Freeman,et al.  An HMM‐based speech recognizer using overlapping articulatory features , 1996 .

[8]  John H. L. Hansen,et al.  A screening test for speech pathology assessment using objective quality measures , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[9]  Christos Georgalas,et al.  Analysis of formant frequencies in patients with oral or oropharyngeal cancers treated by glossectomy. , 2007, International journal of language & communication disorders.

[10]  Koji Takahashi,et al.  Spectral characteristics of hypernasality in maxillectomy patients 1 , 2000 .

[11]  S. Niimi,et al.  A Comparison of Voice Quality Ratings Made by Japanese and American Listeners Using the GRBAS Scale , 2003, Folia Phoniatrica et Logopaedica.

[12]  Frank Fallside,et al.  Neural Networks for Continuous Speech Recognition , 1992 .

[13]  Neil K. Aaronson,et al.  Speech Handicap Index in patients with oral and pharyngeal cancer: Better understanding of patients' complaints , 2008, Head & neck.

[14]  Elina Isotalo,et al.  Speech Aerodynamics and Nasalance in Oral Cancer Patients Treated with Microvascular Transfers , 2005, The Journal of craniofacial surgery.

[15]  Sadaoki Furui,et al.  A Statistical Approach to Automatic Speech Summarization , 2003, EURASIP J. Adv. Signal Process..

[16]  D. Osoba,et al.  The European Organization for Research and Treatment of Cancer QLQ-C30: a quality-of-life instrument for use in international clinical trials in oncology. , 1993, Journal of the National Cancer Institute.

[17]  J. S. Bridle,et al.  An investigation of segmental hidden dynamic models of speech coarticulation for automatic speech recognition , 1998 .

[18]  Kuldip K. Paliwal,et al.  Automatic Speech and Speaker Recognition: Advanced Topics , 1999 .

[19]  Hugo Quené,et al.  Objective Acoustic-Phonetic Speech Analysis in Patients Treated for Oral or Oropharyngeal Cancer , 2009, Folia Phoniatrica et Logopaedica.

[20]  Steve Renals,et al.  THE USE OF RECURRENT NEURAL NETWORKS IN CONTINUOUS SPEECH RECOGNITION , 1996 .

[21]  Elmar Nöth,et al.  Application of Automatic Speech Recognition to Quantitative Assessment of Tracheoesophageal Speech with Different Signal Quality , 2008, Folia Phoniatrica et Logopaedica.

[22]  J. Kreiman,et al.  When and why listeners disagree in voice quality assessment tasks. , 2007, The Journal of the Acoustical Society of America.

[23]  Florien J Koopmans-van Beinum,et al.  Perceptual evaluation of tracheoesophageal speech by naive and experienced judges through the use of semantic differential scales. , 2003, Journal of speech, language, and hearing research : JSLHR.

[24]  隅田 由香,et al.  Digital acoustic analysis of five vowels in maxillectomy patients , 2001 .

[25]  R. Hillman,et al.  Consensus auditory-perceptual evaluation of voice: development of a standardized clinical protocol. , 2009, American journal of speech-language pathology.

[26]  Tara L Whitehill,et al.  Acoustic correlates of hypernasality , 2003, Clinical linguistics & phonetics.

[27]  Daniel Graupe,et al.  Principles of Artificial Neural Networks , 2018, Advanced Series in Circuits and Systems.

[28]  Elmar Nöth,et al.  Intelligibility of laryngectomees’ substitute speech: automatic speech recognition and subjective rating , 2005, European Archives of Oto-Rhino-Laryngology and Head & Neck.

[29]  A. Rademaker,et al.  Functional results of primary closure vs flaps in oropharyngeal reconstruction: a prospective study of speech and swallowing. , 1998, Archives of otolaryngology--head & neck surgery.

[30]  P. Dejonckere,et al.  A basic protocol for functional assessment of voice pathology, especially for investigating the efficacy of (phonosurgical) treatments and evaluating new assessment techniques , 2001, European Archives of Oto-Rhino-Laryngology.

[31]  Nabil Samman,et al.  Acoustic analysis of vowels following glossectomy , 2006, Clinical linguistics & phonetics.

[32]  H. Bartelink,et al.  Multidimensional Assessment of Voice Characteristics After Radiotherapy for Early Glottic Cancer , 1999, The Laryngoscope.

[33]  Li Deng,et al.  Speech recognition using the atomic speech units constructed from overlapping articulatory features , 1994, EUROSPEECH.

[34]  L. Burkhead,et al.  Functional outcomes and rehabilitation strategies in patients treated with chemoradiotherapy for advanced head and neck cancer: a systematic review , 2009, European Archives of Oto-Rhino-Laryngology.

[35]  E. Nöth,et al.  Automatic Quantification of Speech Intelligibility of Adults with Oral Squamous Cell Carcinoma , 2008, Folia Phoniatrica et Logopaedica.

[36]  Ludi E. Smeele,et al.  Functional outcomes and rehabilitation strategies in patients treated with chemoradiotherapy for advanced head and neck cancer: a systematic review , 2008, European Archives of Oto-Rhino-Laryngology.

[37]  Johannes A Langendijk,et al.  Quality of life after surgical treatment for oral and oropharyngeal cancer: a prospective longitudinal assessment of patients reconstructed by a microvascular flap. , 2007, Oral oncology.