gms | German Medical Science

26. Jahrestagung der Deutschen Gesellschaft für Audiologie

Deutsche Gesellschaft für Audiologie e. V.

06.03. - 08.03.2024, Aalen

Introducing an automatic voice and speech screening application for the individual assessment of voice and speech disorders caused by hearing impairments

Meeting Abstract

  • presenting/speaker Alina Ernst - Fraunhofer-Institut für Digitale Medientechnologie IDMT, Institutsteil Hör-, Sprach- und Audiotechnologie HSA, Assistive Sprech- und Sprachanalyse, Oldenburg, Germany
  • Viviane van Diedenhoven-Rasumow - Fraunhofer-Institut für Digitale Medientechnologie IDMT, Institutsteil Hör-, Sprach- und Audiotechnologie HSA, Assistive Sprech- und Sprachanalyse, Oldenburg, Germany
  • Laura Tuschen - Fraunhofer-Institut für Digitale Medientechnologie IDMT, Institutsteil Hör-, Sprach- und Audiotechnologie HSA, Assistive Sprech- und Sprachanalyse, Oldenburg, Germany

Deutsche Gesellschaft für Audiologie e.V.. 26. Jahrestagung der Deutschen Gesellschaft für Audiologie. Aalen, 06.-08.03.2024. Düsseldorf: German Medical Science GMS Publishing House; 2024. Doc104

doi: 10.3205/24dga104, urn:nbn:de:0183-24dga1045

Veröffentlicht: 5. März 2024

© 2024 Ernst et al.
Dieser Artikel ist ein Open-Access-Artikel und steht unter den Lizenzbedingungen der Creative Commons Attribution 4.0 License (Namensnennung). Lizenz-Angaben siehe http://creativecommons.org/licenses/by/4.0/.


Gliederung

Text

Adults with hearing impairment can be affected by associated speech [1] and voice [2] disorders. Here we introduce a screening based on speech processing technologies to identify the limitations of the target group’s communication skills. The technological concept aims to identify changes objectively and automatically in speech and voice production. In this way, speech therapy needs before or after hearing aid and/or CI fitting can be derived in a low-threshold manner and the therapy can be supplemented by an objective progress report [3]. This promotes a more individual hearing-related health care.

The concept, implementation and use of the tool will be discussed at the conference.

To create the screening tool, speech- and voice-related symptoms were identified in connection with hearing-impaired adults. The main characteristics of verbal communication disorders can be seen above all in the voice, pronunciation and prosody, the later analysis modules of the screening. The screening items for the three modules were selected after literature research considering a low screening time and compliance of the analysis targets. The items are verbalized by the user and recorded and processed by the system. The analysis algorithms are designed to provide evident parameters in an automatic and robust way. The analysis modules include procedures to automatically recognize speech and voice activity. This ensures automatic processing of the relevant speech sample parts and sufficient recording quality.

The screening combines items and algorithms to provide distinct parameters for the three analysis modules. The algorithms detect individual pronunciation and prosody changes on word, syllable, and phoneme level, while the voice analysis encompasses multiparametric acoustic analyses and the recording of subjective parameters via questionnaires. The results can be combined to be jointly rated or can stand alone.

The applied screening can be used in many contexts such as clinics, therapy settings, and home evaluation. It can facilitate the assessment for the patients and healthcare practitioners. The integration of the separate, module-based results could provide a patient’s profile to support healthcare processes. Further research into technical and clinical evaluation is needed. Applying the screening may also support and accelerate research in the field of speech and voice disorders caused by hearing impairment.


References

1.
Ruff S, Bocklet T, Nöth E, Müller J, Hoster E, Schuster M. Speech Production Quality of Cochlear Implant Users with Respect to Duration and Onset of Hearing Loss. ORL J Otorhinolaryngol Relat Spec. 2017;79(5):282-94. DOI: 10.1159/000479819 Externer Link
2.
Mora R, Crippa B, Cervoni E, Santomauro V, Guastini L. Acoustic features of voice in patients with severe hearing loss. J Otolaryngol Head Neck Surg. 2012 Feb;41(1):8-13.
3.
Tuschen L. Einsatz von Sprachverarbeitungstechnologien in der Logopädie und Sprachtherapie. Sprache· Stimme· Gehör. 2022;46(01):33-9. DOI: 10.1055/a-1706-9078 Externer Link