Investigating spoken Arabic digits in speech recognition setting

Alotaibi, Yousef Ajami

doi:10.1016/j.ins.2004.07.008

Cited by 37 publications

(22 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Human voice typically has the trait that the signal components possessing lower frequencies encompass higher amplitudes [17], where the higher frequencies encompass comparatively smaller amplitude. In this phenomenon, the higher frequencies (which have lower amplitude) have a lot of chances to be eliminated from the signal in the noise removal process as a noise.…”

Section: Pre-emphasismentioning

confidence: 99%

Artificial Neural Network-Based Speech Recognition Using Dwt Analysis Applied On Isolated Words From Oriental Languages

Rehmam

Halim

Abbas

et al. 2015

MJCS

View full text Add to dashboard Cite

show abstract

Section: Pre-emphasismentioning

confidence: 99%

Artificial Neural Network-Based Speech Recognition Using Dwt Analysis Applied On Isolated Words From Oriental Languages

Rehmam

Halim

Abbas

et al. 2015

MJCS

View full text Add to dashboard Cite

show abstract

“…Malay digits has reported a recognition rate of 80.5% and 90.7% when dynamic time warping and Hidden Markov Model (HMM) techniques were used respectively (Al-Haddad et al, 2008), whereas recognition rates of 98% (Azam et al, 2007), 99.5% (Alotaibi, 2005) and 98.125% to 100% (Dede et al, 2010) were reported in a similar application using neural networks.…”

Section: Automatic Speech Recognitionmentioning

confidence: 99%

Automatic Recognition of Speech-evoked Brainstem Responses to English Vowels

Samimi

Forouzanfar

Dajani

2015

Modelling, Identification and Control / 827: Computational Intelligence

View full text Add to dashboard Cite

The objective of this study is to investigate automatic recognition of speech-evoked auditory brainstem responses (speech-evoked ABR) to the five English vowels (/a/, /ae/, /ao (ɔ)/, /i/ and /u/). We used different automatic speech recognition methods to discriminate between the responses to the vowels. The best recognition result was obtained by applying principal component analysis (PCA) on the amplitudes of the first ten harmonic components of the envelope following response (based on spectral components at fundamental frequency and its harmonics) and of the frequency following response (based on spectral components in first formant region) and combining these two feature sets. With this combined feature set used as input to an artificial neural network, a recognition accuracy of 83.8% was achieved. This study could be extended to more complex stimuli to improve assessment of the auditory system for speech communication in hearing impaired individuals, and potentially help in the objective fitting of hearing aids.iii

show abstract

“…Due to the relevance of this problem, several papers have been published, trying to improve digit recognition in different languages, such as English (NIMJE; SHANDILYA, 2011), Portuguese (SILVA et al, 2012), Arabic (ALOTAIBI, 2005) and Mandarin (SHYU et al, 2000).…”

Section: Introductionmentioning

confidence: 99%

<b>A comparative study between MFCC and LSF coefficients in automatic recognition of isolated digits pronounced in Portuguese and English</b> - doi: 10.4025/actascitechnol.v35i4.19825

2013

View full text Add to dashboard Cite

Recognition of isolated spoken digits is the core procedure for a large number of applications which rely solely on speech for data exchange, as in telephone-based services, such as dialing, airline reservation, bank transaction and price quotation. Spoken digit recognition is generally a challenging task since the signals last for a short period of time and often some digits are acoustically very similar to other digits. The objective of this paper is to investigate the use of machine learning algorithms for spoken digit recognition and disclose the free availability of a database with digits pronounced in English and Portuguese to the scientific community. Since machine learning algorithms are fully dependent on predictive attributes to build precise classifiers, we believe that the most important task for successfully recognizing spoken digits is feature extraction. In this work, we show that Line Spectral Frequencies (LSF) provide a set of highly predictive coefficients. We evaluated our classifiers in different settings by altering the sampling rate to simulate low quality channels and varying the number of coefficients.

show abstract

Investigating spoken Arabic digits in speech recognition setting

Cited by 37 publications

References 13 publications

Artificial Neural Network-Based Speech Recognition Using Dwt Analysis Applied On Isolated Words From Oriental Languages

Artificial Neural Network-Based Speech Recognition Using Dwt Analysis Applied On Isolated Words From Oriental Languages

Automatic Recognition of Speech-evoked Brainstem Responses to English Vowels

<b>A comparative study between MFCC and LSF coefficients in automatic recognition of isolated digits pronounced in Portuguese and English</b> - doi: 10.4025/actascitechnol.v35i4.19825

Contact Info

Product

Resources

About