Evaluating vowel pronunciation quality: Formant space matching versus ASR confidence scoring

Patil, Ashish; Gupta, Chitralekha; Rao, Preeti

doi:10.1109/ncc.2010.5430187

Cited by 7 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have presented the results of a study examining the utility of spectral features of vowels in the automated assessment of non-native English speech. Previous studies ( [9], [10]) have used vowel space size (or vowel dispersion) as a measure of accuracy in L2 pronunciation. However, the theoretical basis for this assumption remains unclear.…”

Section: Discussionmentioning

confidence: 99%

“…Recent studies that have examined the use of formant characteristics in the automated assessment of speech intelligibility (e.g. [9]; [10]) have established a link between proficiency and vowel formant characteristics. It is regrettable, however, that no serious attempt has been made in the vast majority of these studies to normalise speaker differences in vocal tract sizes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Vowel Characteristics in the Assessment of L2 English Pronunciation

2016

View full text Add to dashboard Cite

There is considerable need to utilise linguistically meaningful measures of second language (L2) proficiency that are based on perceptual cues used by humans to assess pronunciation. Previous research on non-native acquisition of vowel systems suggests a strong link between vowel production accuracy and speech intelligibility. It is well known that the acoustic and perceptual identification of vowels rely on formant frequencies. However, formant analysis may not be viable in large-scale corpus research, given the need for manual correction of tracking errors. Spectral analysis techniques have been shown to be a robust alternative to formant tracking. This paper explores the use of one such technique-the discrete cosine transform (DCT)-for modelling English vowel spectra in the productions of non-native English speakers. Mel-scaled DCT coefficients were calculated over a frequency band of 200-4000 Hz. Results show a statistically significant correlation between coefficients and the proficiency level of speakers, and suggest that this technique holds some promise in automated L2 pronunciation teaching and assessment.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Vowel Characteristics in the Assessment of L2 English Pronunciation

2016

View full text Add to dashboard Cite

show abstract

“…These vector positions of the formants are used to characterize a particular vowel. The first two formants (F 1 , F 2 ) of a vowel utterance cue the phonemic identity of the vowel (Patil et al, 2010). The third formant F 3 is also important for vowel categorisation (Kiefte et al, 2010).…”

Section: Frequency Formantsmentioning

confidence: 99%

Smooth Formant Peak Via Discrete Tchebichef Transform

Abu¹,

Ernawan²,

Salim³

2015

Journal of Computer Science

View full text Add to dashboard Cite

With the growth in computing power, speech recognition carries a strong potential in the near future. It has even become increasingly popular with the development of mobile devices. Presumably, mobile devices have limited computational power, memory size and battery life. In general, speech recognition operation requires heavy computation due to large samples per window used. Fast Fourier Transfom (FFT) is the most popular transform to search for formant frequencies in speech recognition. In addition, FFT operates in complex fields with imaginary numbers. This paper proposes an approach based on Discrete Tchebichef Transform (DTT) as a possible alternative to FFT in searching for the formant frequencies. The experimental outputs in terms of the frequency formants using FFT and DTT have been compared. Interestingly, the experimental results show that both have produced relatively identical formant shape output in terms of basic vowels and consonants recognition. DTT has the same capability to recognize speech formants F 1 , F 2 , F 3 on real domains.

show abstract

“…Formants are a characteristic resonant region of a sound. Formants are exactly the resonant frequencies of vocal tract [14]. The frequency formants of the vowel 'O' and the consonant 'RA' have been extracted using 256 DTT as presented in Fig.…”

Section: Frequency Formantsmentioning

confidence: 99%

Efficient Discrete Tchebichef on SpectrumAnalysis of Speech Recognition

Ernawan¹,

Abu²

2011

IJMLC

View full text Add to dashboard Cite

Speech recognition is still a growing field of importance. The growth in computing power will open its strong potentials for full use in the near future. Spectrum analysis is an elementary operation in speech recognition. Fast Fourier Transform (FFT) has been a traditional technique to analyze frequency spectrum of the signals in speech recognition. FFT is computationally complex especially with imaginary numbers. The Discrete Tchebichef Transform (DTT) is proposed instead of the popular FFT. DTT has lower computational complexity and it does not require complex transform dealing with imaginary numbers. This paper proposes a novel approach based on 256 discrete orthonormal Tchebichef polynomials as efficient technique to analyze a vowel and a consonant in spectral frequency of speech recognition. The comparison between 1024 discrete orthonormal Tchebichef transform and 256 discrete orthonormal Tchebichef transform has been done. The preliminary experimental results show that 256 DTT has the potential to be more efficient to transform time domain into frequency domain for speech recognition. 256 DTT produces simpler output than 1024 DTT in frequency spectrum. At the same time, 256 Discrete Tchebichef Transform can produce concurrently four formants F 1 , F 2 , F 3 and F 4 .

show abstract

Evaluating vowel pronunciation quality: Formant space matching versus ASR confidence scoring

Cited by 7 publications

References 7 publications

Vowel Characteristics in the Assessment of L2 English Pronunciation

Vowel Characteristics in the Assessment of L2 English Pronunciation

Smooth Formant Peak Via Discrete Tchebichef Transform

Efficient Discrete Tchebichef on SpectrumAnalysis of Speech Recognition

Contact Info

Product

Resources

About