Application of Automatic Speech Recognition to Quantitative Assessment of Tracheoesophageal Speech with Different Signal Quality

dc.contributor.authorHaderlein, Tino
dc.contributor.authorRiedhammer, Korbinian
dc.contributor.authorNöth, Elmar
dc.contributor.authorToy, Hikmet
dc.contributor.authorSchuster, Maria
dc.contributor.authorEysholdt, Ulrich
dc.contributor.authorHornegger, Joachim
dc.contributor.authorRosanowski, Frank
dc.date.accessioned2013-03-14
dc.date.available2023-10-06T13:15:20Z
dc.date.created2008
dc.date.issued2013-03-14
dc.description.abstractObjective: Tracheoesophageal voice is state-of-the-art in voice rehabilitation after laryngectomy. Intelligibility on a telephone is an important evaluation criterion as it is a crucial part of social life. An objective measure of intelligibility when talking on a telephone is desirable in the field of postlaryngectomy speech therapy and its evaluation. Patients and Methods: Based upon successful earlier studies with broadband speech, an automatic speech recognition (ASR) system was applied to 41 recordings of postlaryngectomy patients. Recordings were available in different signal qualities; quality was the crucial criterion for this study. Results: Compared to the intelligibility rating of 5 human experts, the ASR system had a correlation coefficient of r = –0.87 and Krippendorff’s _ of 0.65 when broadband speech was processed. The rater group alone achieved _ = 0.66. With the test recordings in telephone quality, the system reached r = –0.79 and _ = 0.67. Conclusion: For medical purposes, a comprehensive diagnostic approach to (substitute) voice has to cover both subjective and objective tests. An auto- matic recognition system such as the one proposed in this study can be used for objective intelligibility rating with results comparable to those of human experts. This holds for broadband speech as well as for automatic evaluation via telephone.en
dc.identifier.citationFolia Phoniatrica et Logopaedica 2009; 61: 12-17. <http://content.karger.com/ProdukteDB/produkte.asp?typ=pdf&doi=187620> © 2008 S. Karger AG, Basel
dc.identifier.opus-id3154
dc.identifier.urihttps://open.fau.de/handle/openfau/3154
dc.identifier.urnurn:nbn:de:bvb:29-opus-44245
dc.language.isoen
dc.subjectLaryngectomy
dc.subjectSubstitute speech
dc.subjectAutomatic speech recognition
dc.subjectAgreement measures
dc.subject.ddcDDC Classification::6 Technik, Medizin, angewandte Wissenschaften :: 61 Medizin und Gesundheit :: 610 Medizin und Gesundheit
dc.titleApplication of Automatic Speech Recognition to Quantitative Assessment of Tracheoesophageal Speech with Different Signal Qualityen
dc.typearticle
dcterms.publisherFriedrich-Alexander-Universität Erlangen-Nürnberg (FAU)
local.journal.titleFolia Phoniatrica et Logopaedica 2009; 61: 12-17. <http://content.karger.com/ProdukteDB/produkte.asp?typ=pdf&doi=187620> © 2008 S. Karger AG, Basel
local.sendToDnbfree*
local.subject.fakultaetMedizinische Fakultät / Medizinische Fakultät -ohne weitere Spezifikation-
local.subject.gnd-
local.subject.sammlungUniversität Erlangen-Nürnberg / Nationallizenzen: Alle Beiträge sind mit Zustimmung der Rechteinhaber aufgrund einer DFG-geförderten Nationallizenz frei zugänglich. / Nationallizenzen 2008
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
3154_fpl2009061001012.pdf
Size:
139.03 KB
Format:
Adobe Portable Document Format
Description: