2022
DOI: 10.3389/fneur.2021.724800
|View full text |Cite
|
Sign up to set email alerts
|

Visualization of Speech Perception Analysis via Phoneme Alignment: A Pilot Study

Abstract: Objective: Speech tests assess the ability of people with hearing loss to comprehend speech with a hearing aid or cochlear implant. The tests are usually at the word or sentence level. However, few tests analyze errors at the phoneme level. So, there is a need for an automated program to visualize in real time the accuracy of phonemes in these tests.Method: The program reads in stimulus-response pairs and obtains their phonemic representations from an open-source digital pronouncing dictionary. The stimulus ph… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
2
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
2

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(2 citation statements)
references
References 47 publications
0
2
0
Order By: Relevance
“…In addition, the use of ASR could open venues to improved (automated) scoring methods in audiology tests. Ratnanather et al ( 51 ) demonstrated how one can automate the alignment of phonemes based on the minimum edit distance between the source speech and the utterances of the subject in real time. Visualizing this alignment may provide insights to clinicians about what phonological errors are made.…”
Section: Discussionmentioning
confidence: 99%
“…In addition, the use of ASR could open venues to improved (automated) scoring methods in audiology tests. Ratnanather et al ( 51 ) demonstrated how one can automate the alignment of phonemes based on the minimum edit distance between the source speech and the utterances of the subject in real time. Visualizing this alignment may provide insights to clinicians about what phonological errors are made.…”
Section: Discussionmentioning
confidence: 99%
“…Responses to open-set sentences, especially when presented in background noise, include insertions (i.e., reporting words or phonemes that were not presented, or false starts such as "um") and deletions (i.e., not reporting words or phonemes that were presented), which makes it extremely difficult to create a one-to-one mapping of response phonemes to stimulus phonemes that is necessary for analyzing consonant feature errors. Automatic phoneme alignment algorithms have been developed for open-set responses to sentence-length stimuli (Bernstein et al, 1994(Bernstein et al, , 2021Ratnanather et al, 2022) in order to generate consonant confusion matrices (CMs) for sentence stimuli. However, consonant feature analysis based on such CMs is confounded by the context information in meaningful words and sentences.…”
mentioning
confidence: 99%