Test Data Combination Strategy for Effective Test Suite Generation

Yoon, Jae Hoon; Kang, Jeong Seok; Park, Hong Seong

doi:10.1109/icitcs.2013.6717891

Cited by 3 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used a modified version of the quilting algorithm ( Overath and Lee 2017 ) where we pseudorandomized the order of phonemes (instead of set segment lengths). First, phonemes were extracted from the recordings and corresponding transcripts using the Penn Phonetic Lab Forced Aligner ( https://babel.ling.upenn.edu/phonetics/old_website_2015/p2fa/index.html ) ( Yuan and Liberman 2008 ) for English speech and the Korean Phonetic Aligner ( https://korean.utsc.utoronto.ca/kpa/ ; Yoon and Kang 2013 ) for Korean speech. The phoneme segmentation output was a Praat TextGrid, which was then imported to MATLAB ( https://github.com/bbTomas/mPraat ) via the mPraat toolbox ( Bořil and Skarnitzl 2016 ).…”

Section: Methodsmentioning

confidence: 99%

Linguistic modulation of the neural encoding of phonemes

Kim,

De Martino,

Overath

2024

Cerebral Cortex

View full text Add to dashboard Cite

Speech comprehension entails the neural mapping of the acoustic speech signal onto learned linguistic units. This acousto-linguistic transformation is bi-directional, whereby higher-level linguistic processes (e.g. semantics) modulate the acoustic analysis of individual linguistic units. Here, we investigated the cortical topography and linguistic modulation of the most fundamental linguistic unit, the phoneme. We presented natural speech and “phoneme quilts” (pseudo-randomly shuffled phonemes) in either a familiar (English) or unfamiliar (Korean) language to native English speakers while recording functional magnetic resonance imaging. This allowed us to dissociate the contribution of acoustic vs. linguistic processes toward phoneme analysis. We show that (i) the acoustic analysis of phonemes is modulated by linguistic analysis and (ii) that for this modulation, both of acoustic and phonetic information need to be incorporated. These results suggest that the linguistic modulation of cortical sensitivity to phoneme classes minimizes prediction error during natural speech perception, thereby aiding speech comprehension in challenging listening situations.

show abstract

Section: Methodsmentioning

confidence: 99%

Linguistic modulation of the neural encoding of phonemes

Kim,

De Martino,

Overath

2024

Cerebral Cortex

View full text Add to dashboard Cite

show abstract

“…The PH onset impulse train and the ENV of the natural sentences were used as speech (stimuli) features. All PH onsets in the sentences were automatically identified ( Yoon and Kang, 2013 ) using Praat software (University of Amsterdam, Netherlands) and manually confirmed. The number of phonemes in each sentence ranged from 17 to 22 (mean: 18.6, standard deviation: 3.9).…”

Section: Methodsmentioning

confidence: 99%

Objective speech intelligibility prediction using a deep learning model with continuous speech-evoked cortical auditory responses

Joo

Trang

et al. 2022

Front. Neurosci.

View full text Add to dashboard Cite

Auditory prostheses provide an opportunity for rehabilitation of hearing-impaired patients. Speech intelligibility can be used to estimate the extent to which the auditory prosthesis improves the user’s speech comprehension. Although behavior-based speech intelligibility is the gold standard, precise evaluation is limited due to its subjectiveness. Here, we used a convolutional neural network to predict speech intelligibility from electroencephalography (EEG). Sixty-four–channel EEGs were recorded from 87 adult participants with normal hearing. Sentences spectrally degraded by a 2-, 3-, 4-, 5-, and 8-channel vocoder were used to set relatively low speech intelligibility conditions. A Korean sentence recognition test was used. The speech intelligibility scores were divided into 41 discrete levels ranging from 0 to 100%, with a step of 2.5%. Three scores, namely 30.0, 37.5, and 40.0%, were not collected. The speech features, i.e., the speech temporal envelope (ENV) and phoneme (PH) onset, were used to extract continuous-speech EEGs for speech intelligibility prediction. The deep learning model was trained by a dataset of event-related potentials (ERP), correlation coefficients between the ERPs and ENVs, between the ERPs and PH onset, or between ERPs and the product of the multiplication of PH and ENV (PHENV). The speech intelligibility prediction accuracies were 97.33% (ERP), 99.42% (ENV), 99.55% (PH), and 99.91% (PHENV). The models were interpreted using the occlusion sensitivity approach. While the ENV models’ informative electrodes were located in the occipital area, the informative electrodes of the phoneme models, i.e., PH and PHENV, were based on the occlusion sensitivity map located in the language processing area. Of the models tested, the PHENV model obtained the best speech intelligibility prediction accuracy. This model may promote clinical prediction of speech intelligibility with a comfort speech intelligibility test.

show abstract

“…We used a modified version of the quilting algorithm (Overath and Lee, 2017; Overath and Paik, 2021) where we pseudorandomized the order of phonemes (instead of set segment lengths). First, phonemes were extracted from the recordings and corresponding transcripts using the Penn Phonetic Lab Forced Aligner 1 (Yuan and Liberman, 2008) for English speech and the Korean Phonetic Aligner 2 (Yoon and Kang, 2013) for Korean speech. The phoneme segmentation output was a Praat TextGrid, which was then imported to MATLAB 3 via the mPraat toolbox (Bořil and Skarnitzl, 2016).…”

Section: Methodsmentioning

confidence: 99%

Linguistic modulation of the neural encoding of phonemes

Kim

Martino

Overath

2021

Preprint

View full text Add to dashboard Cite

Speech comprehension entails the neural mapping of the acoustic speech signal onto learned linguistic units. This acousto-linguistic transformation is bi-directional, whereby higher-level linguistic processes (e.g., semantics) modulate the acoustic analysis of individual linguistic units. Here, we investigated the cortical topography and linguistic modulation of the most fundamental linguistic unit, the phoneme. We presented natural speech and 'phoneme quilts' (pseudo-randomly shuffled phonemes) in either a familiar (English) or unfamiliar (Korean) language to native English speakers while recording fMRI. This design dissociates the contribution of acoustic and linguistic processes towards phoneme analysis. We show that (1) the four main phoneme classes (vowels, nasals, plosives, fricatives) are differentially and topographically encoded in human auditory cortex, and that (2) their acoustic analysis is modulated by linguistic analysis. These results suggest that the linguistic modulation of cortical sensitivity to phoneme classes minimizes prediction error during natural speech perception, thereby aiding speech comprehension in challenging listening situations.

show abstract

Test Data Combination Strategy for Effective Test Suite Generation

Abstract: Begin f i =SelectFactor(F); Create a test suite T with v[i] empty test datas; Assign v[i] values of f i into T; F=F-{f i }; F deal ={f i }; while F ≠ F i =SelectFactor(F) Inters={r k ∩(F deal +{f i })|f i ∈r k , k=1,2,…,m};

Cited by 3 publications

References 6 publications

Linguistic modulation of the neural encoding of phonemes

Linguistic modulation of the neural encoding of phonemes

Objective speech intelligibility prediction using a deep learning model with continuous speech-evoked cortical auditory responses

Linguistic modulation of the neural encoding of phonemes

Contact Info

Product

Resources

About