Automated Intelligibility Assessment of Pathological Speech Using Phonological Features
It is commonly acknowledged that word or phoneme intelligibility is an important criterion in the assessment of the communication efficiency of a pathological speaker. People have therefore put a lot of effort in the design of perceptual intelligibility rating tests. These tests usually have the dra...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2009-01-01
|
| Series: | EURASIP Journal on Advances in Signal Processing |
| Online Access: | http://dx.doi.org/10.1155/2009/629030 |
| _version_ | 1818205913500090368 |
|---|---|
| author | Catherine Middag Jean-Pierre Martens Gwen Van Nuffelen Marc De Bodt |
| author_facet | Catherine Middag Jean-Pierre Martens Gwen Van Nuffelen Marc De Bodt |
| author_sort | Catherine Middag |
| collection | DOAJ |
| description | It is commonly acknowledged that word or phoneme intelligibility is an important criterion in the assessment of the communication efficiency of a pathological speaker. People have therefore put a lot of effort in the design of perceptual intelligibility rating tests. These tests usually have the drawback that they employ unnatural speech material (e.g., nonsense words) and that they cannot fully exclude errors due to listener bias. Therefore, there is a growing interest in the application of objective automatic speech recognition technology to automate the intelligibility assessment. Current research is headed towards the design of automated methods which can be shown to produce ratings that correspond well with those emerging from a well-designed and well-performed perceptual test. In this paper, a novel methodology that is built on previous work (Middag et al., 2008) is presented. It utilizes phonological features, automatic speech alignment based on acoustic models that were trained on normal speech, context-dependent speaker feature extraction, and intelligibility prediction based on a small model that can be trained on pathological speech samples. The experimental evaluation of the new system reveals that the root mean squared error of the discrepancies between perceived and computed intelligibilities can be as low as 8 on a scale of 0 to 100. |
| first_indexed | 2024-12-12T04:04:41Z |
| format | Article |
| id | doaj.art-4cc8ae0015b045f08092f5bb94d84620 |
| institution | Directory Open Access Journal |
| issn | 1687-6172 1687-6180 |
| language | English |
| last_indexed | 2024-12-12T04:04:41Z |
| publishDate | 2009-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Advances in Signal Processing |
| spelling | doaj.art-4cc8ae0015b045f08092f5bb94d846202022-12-22T00:38:48ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61721687-61802009-01-01200910.1155/2009/629030Automated Intelligibility Assessment of Pathological Speech Using Phonological FeaturesCatherine MiddagJean-Pierre MartensGwen Van NuffelenMarc De BodtIt is commonly acknowledged that word or phoneme intelligibility is an important criterion in the assessment of the communication efficiency of a pathological speaker. People have therefore put a lot of effort in the design of perceptual intelligibility rating tests. These tests usually have the drawback that they employ unnatural speech material (e.g., nonsense words) and that they cannot fully exclude errors due to listener bias. Therefore, there is a growing interest in the application of objective automatic speech recognition technology to automate the intelligibility assessment. Current research is headed towards the design of automated methods which can be shown to produce ratings that correspond well with those emerging from a well-designed and well-performed perceptual test. In this paper, a novel methodology that is built on previous work (Middag et al., 2008) is presented. It utilizes phonological features, automatic speech alignment based on acoustic models that were trained on normal speech, context-dependent speaker feature extraction, and intelligibility prediction based on a small model that can be trained on pathological speech samples. The experimental evaluation of the new system reveals that the root mean squared error of the discrepancies between perceived and computed intelligibilities can be as low as 8 on a scale of 0 to 100.http://dx.doi.org/10.1155/2009/629030 |
| spellingShingle | Catherine Middag Jean-Pierre Martens Gwen Van Nuffelen Marc De Bodt Automated Intelligibility Assessment of Pathological Speech Using Phonological Features EURASIP Journal on Advances in Signal Processing |
| title | Automated Intelligibility Assessment of Pathological Speech Using Phonological Features |
| title_full | Automated Intelligibility Assessment of Pathological Speech Using Phonological Features |
| title_fullStr | Automated Intelligibility Assessment of Pathological Speech Using Phonological Features |
| title_full_unstemmed | Automated Intelligibility Assessment of Pathological Speech Using Phonological Features |
| title_short | Automated Intelligibility Assessment of Pathological Speech Using Phonological Features |
| title_sort | automated intelligibility assessment of pathological speech using phonological features |
| url | http://dx.doi.org/10.1155/2009/629030 |
| work_keys_str_mv | AT catherinemiddag automatedintelligibilityassessmentofpathologicalspeechusingphonologicalfeatures AT jeanpierremartens automatedintelligibilityassessmentofpathologicalspeechusingphonologicalfeatures AT gwenvannuffelen automatedintelligibilityassessmentofpathologicalspeechusingphonologicalfeatures AT marcdebodt automatedintelligibilityassessmentofpathologicalspeechusingphonologicalfeatures |