The evaluation of the degree of speech impairment and the utility of computer recognition of impaired speech are separately and independently performed. Particular attention is paid to the question concerning whether or not there is a relationship between naive listeners' subjective judgments of impaired speech and the performance of a laboratory version of a speech recognition system. It is a difficult task to relate a speech impairment rating with speech recognition accuracy. Towards this end, a statistical causal model is proposed. This model is very appealing in its structure to support inference, and thus can be applied to perform various assessments such as the success of automatic recognition of dysarthric speech. The application of this model is illustrated with a case study of a dysarthric speaker compared against a normal speaker serving as a control. >

A statistical causal model for the assessment of dysarthric speech and the utility of computer-based speech recognition

The article studies age related variations of speech characteristics of two age groups, in the Bengali language. The study considers 60 speakers in the each age groups, 60---80 years and 20---40 years, respectively. We have considered different voice source features like fundamental frequency, formant frequencies, jitter, shimmer and harmonic to noise ratio. Cepstral domain feature, Mel Frequency Cepstral coefficients (MFCC) of different voiced Bengali vowels are also analyzed for younger and older adult groups. MFCC feature and Hidden Markov model parameter of different voiced vowels are used to study phoneme dissimilarities measure between two age groups. Age related changes in elderly speech affect the automatic speech recognition performance as was observed in our study, raising the need for specific acoustic models for elderly persons.

/pdf/effect-of-aging-on-speech-features-and-phoneme-recognition-a-1b0b9ra6nu.pdf

Effect of aging on speech features and phoneme recognition: a study on Bengali voicing vowels

https://maxwell.ict.griffith.edu.au/spl/publications/papers/spcom11_stark_mmsefbe.pdf

MMSE estimation of log-filterbank energies for robust speech recognition

Isolated Automatic Speech Recognition of Quechua Numbers using MFCC, DTW AND KNN Reconocimiento Automático de Habla Aislado de Números en Quechua usando MFCC, DTW AND KNN

Spoken English learning has always been the largest obstacle to the English communicative competence of Chinese students. This paper adopts the in-depth learning method based on computer-aided speech recognition technology to achieve the automatic speech recognition of spoken English and to overcome the defects of spoken speech evaluation in the traditional mode such as fairly high subjectivity and low evaluation efficiency. Meanwhile, the evaluation method of the traditional computer-aided spoken speech quality has been improved, and multi-parameter indicators such as accuracy, speed, rhythm and intonation have been taken into account. Through the establishment of the objective and efficient spoken English speech recognition and evaluation model, we are able to provide true and credible evaluations and timely feedback guidance for learners. The research results effectively guide learners to study spoken English, which uplifts the existing level of spoken English learning in China.

Jared Bernstein

Papers

Automatic speech recognition of impaired speech