Carcinologic Speech Severity Index Project: A Database of Speech Disorder Productions to Assess Quality of Life Related to Speech After Cancer

Carcinologic Speech Severity Index Project: A Database of Speech Disorder Productions to Assess Quality of Life Related to Speech After Cancer Corine Astésano1, Mathieu Balaguer2, Jérôme Farinas1, Corinne Fredouille3, Pascal Gaillard1, Alain Ghio4, Laurence Giusti4, Imed Laaridh3, Muriel Lalain4, Benoît Lepage1, Julie Mauclair1,5, Olivier Nocaudie1, Julien Pinquier1, Oriol Pont1, Gilles Pouchoulin4, Michèle Puech2, Danièle Robert4, Etienne Sicard1, Virginie Woisard2 1Toulouse University, 2Toulouse Hospital, 3University of Avignon, LIA,4Aix-Marseille Univ, CNRS, LPL, 5Paris Descartes University Toulouse France, Toulouse France, Avignon France, Aix-en-Provence France, Paris France c2si@irit.fr Abstract Within the framework of the Carcinologic Speech Severity Index (C2SI) InCA Project, we collected a large database of French speech recordings aiming at validating Disorder Severity Indexes. Such a database will be useful for measuring the impact of oral and pharyngeal cavity cancer on speech production. That will permit to assess patients’ Quality of Life after treatment. The database is composed of audio recordings from 135 speakers and associated metadata. Several intelligibility and comprehensibility levels of speech functions have been evaluated. Acoustics and Prosody have been assessed. Perceptual evaluation rates from both naive and expert juries are being produced. Automatic analyzes are being carried out. That will provide to speech therapists objective tools to take into account the intelligibility and comprehensibility of patients which received cancer treatment (surgery and/or radiotherapy and/or chemotherapy). The aim of this paper is to justify the need of this corpus and his data collection. This corpus will be available to the scientific community through the GIS Parolotheque. Keywords: speech intelligibility and comprehensibility, quality of life assessment, speech corpus, pathological speech 1. Introduction The decreasing mortality in cancerology highlights the importance to reduce the impact on the Quality of Life (QoL) after cancer. That particularly concerns Head and Neck Cancers (HNC), because their treatment can be mutilating and disabling. However, the usual tools for assessing QoL are not relevant for measuring the impact of the treatment on the main functions involved by the sequelae. And, there is a clear lack of uniform methods for assessing functional outcomes. Measuring the impact on one or several of the most altered functions after the therapeutic care of a given tumoral localization, would allow: 1. to complete the expression of the therapeutic outcomes by functional forecast index, 2. to adjust the treatment for reducing their functional consequences. For the HNC, it is mainly about impacts of (oral) communication and feeding (swallowing) (Mlynarek AM et al 2008). QoL research has, at times, failed to provide health care professionals with clinically relevant and interpretable information that can guide treatment decisions. This has led researchers to attempt to make commonly used research tools more accessible to the clinicians. Health-related Quality of Life (HRQoL) reflecting the effect of disease and disease treatment on general well being (Cardol M et al 1999) evolved to the creation of handicap questionnaires and specific related QoL questionnaires for numerous chronic diseases with a rise in importance of specific and symptom modules. But validated tools to measure the functional outcomes of carcinologic treatment are …

Content truncated to 500 words