Abstract:Many speakers with dysarthria have reduced intelligibility[,] and improving intelligibility is often a primary intervention objective. Consequently, measurement of intelligibility provides important information that is useful for clinical decision-making. The present study compared two different measures of intelligibility obtained in audio-only and audio-visual modalities for 4 different speakers with dysarthria (2 with mild-moderate dysarthria; 2 with severe dysarthria) secondary to cerebral palsy. A total o… Show more
“…When comparing the percentage scores obtained for the different measures, results show, first, that word level scoring produces higher intelligibility scores than utterance level scoring. This is in line with earlier research [11] suggesting that when using subjective rating scales, raters tend to underestimate the extent to which speakers are intelligible. A rater may, for example, understand every word, but still judge intelligibility as less than perfect when higherthan-normal listening effort is required because of articulatory irregularities.…”
Section: Comparisons Between Scores At Different Levels Of Granularitysupporting
confidence: 92%
“…to listen to speech fragments and write down what they hear (e.g., [11,2,12]). For this form of intelligibility measurement, different types of speech material can be used, including isolated words or pseudowords, whole sentences, and Semantically Unpredictable Sentences (SUS) [3].…”
Section: Introductionmentioning
confidence: 99%
“…In general, orthographic transcriptions of regular or SUS sentences are scored at the word level: each word is scored as either correct or incorrect [11,18]. Yet, both Hustad et al [1] and Beijer et al [19] argue that such word level scoring may still be quite broad, suggesting that it may be necessary to also collect judgments at even finer levels of granularity, i.e.…”
Measuring the intelligibility of disordered speech is a common practice in both clinical and research contexts. Over the years various methods have been proposed and studied, including methods relying on subjective ratings by human judges, and objective methods based on speech technology. Many of these methods measure speech intelligibility at the speaker or utterance level. While this may be satisfactory for some purposes, more detailed evaluations might be required in other cases such as diagnosis and measuring or comparing the outcomes of different types of therapy (by humans or computer programs). In the current paper we investigate intelligibility ratings at three different levels of granularity: utterance, word, and subword level. In a web experiment 50 speech fragments produced by seven dysarthric speakers were rated by 36 listeners in three ways: a score per utterance on a Visual Analogue and a Likert scale, and an orthographic transcription. The latter was used to obtain word and subword (grapheme and phoneme) level ratings using automatic alignment and conversion methods. The implemented phoneme scoring method proved feasible, reliable, and provided a more sensitive and informative measure of intelligibility. Possible implications for clinical practice and research are discussed.
“…When comparing the percentage scores obtained for the different measures, results show, first, that word level scoring produces higher intelligibility scores than utterance level scoring. This is in line with earlier research [11] suggesting that when using subjective rating scales, raters tend to underestimate the extent to which speakers are intelligible. A rater may, for example, understand every word, but still judge intelligibility as less than perfect when higherthan-normal listening effort is required because of articulatory irregularities.…”
Section: Comparisons Between Scores At Different Levels Of Granularitysupporting
confidence: 92%
“…to listen to speech fragments and write down what they hear (e.g., [11,2,12]). For this form of intelligibility measurement, different types of speech material can be used, including isolated words or pseudowords, whole sentences, and Semantically Unpredictable Sentences (SUS) [3].…”
Section: Introductionmentioning
confidence: 99%
“…In general, orthographic transcriptions of regular or SUS sentences are scored at the word level: each word is scored as either correct or incorrect [11,18]. Yet, both Hustad et al [1] and Beijer et al [19] argue that such word level scoring may still be quite broad, suggesting that it may be necessary to also collect judgments at even finer levels of granularity, i.e.…”
Measuring the intelligibility of disordered speech is a common practice in both clinical and research contexts. Over the years various methods have been proposed and studied, including methods relying on subjective ratings by human judges, and objective methods based on speech technology. Many of these methods measure speech intelligibility at the speaker or utterance level. While this may be satisfactory for some purposes, more detailed evaluations might be required in other cases such as diagnosis and measuring or comparing the outcomes of different types of therapy (by humans or computer programs). In the current paper we investigate intelligibility ratings at three different levels of granularity: utterance, word, and subword level. In a web experiment 50 speech fragments produced by seven dysarthric speakers were rated by 36 listeners in three ways: a score per utterance on a Visual Analogue and a Likert scale, and an orthographic transcription. The latter was used to obtain word and subword (grapheme and phoneme) level ratings using automatic alignment and conversion methods. The implemented phoneme scoring method proved feasible, reliable, and provided a more sensitive and informative measure of intelligibility. Possible implications for clinical practice and research are discussed.
“…Further research is needed to explore the relationships among speech treatment, expansion of vowel space, intelligibility, and communicative participation by children with CP. More objective measures of intelligibility, such as percentage of vowels accurately transcribed orthographically (Hustad, 2006), are underway in the Speech Production and Perception Lab. Results suggest that special attention should be paid to treating children ' s front and low vowel productions, as these are the least intelligible vowels for most of our participants (Levy, Seid, Chen, Leone, Moya-Gale, Hsu, et al, 2014).…”
“…This is in contrast to related questions on the intelligibility and naturalness of synthesized speech, where researchers agreed on a number of well-documented protocols to assess these aspects of computer speech (see the Blizzard Challenge, a yearly competition among speech synthesis systems based on corpora, see http://www.cs.cmu.edu/~awb/). For a review of problems encountered in subjective methods to assess intelligibility we refer to Beijer, Clapham & Rietveld (submitted) and Hustad (2006). Even if the correct operationalizations are available, a number of other questions have to be answered before ecologically valid effectiveness studies can be carried out.…”
Section: B) Clinical Utility Of Telehealth Should Be Establishedmentioning
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.