Classification techniques for automatic speech recognition (ASR) algorithms used with real time speech translation

• Published in: 2017 Computing Conference : 18-20 July 2017 pp. 200 - 207
• Main Authors: Nasereddin, Hebah H. O., Omari, Ayoub Abdel Rahman
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.07.2017
• Subjects: Acoustics; AF (Acoustic Feature); AM (Acoustic Model); ANN (Artificial Neural Network); ASR (Automatic Speech Recognition); Bayes methods; BN (Bayesian Network); CNN (Convolutional Neural Networks); CVC (Consonant-Vowel-Consonant); DAG (Direct Acyclic Graph); DBN (Dynamic Bayesian Networks); DCT (Discrete Cosine Transformation); DNN (Deep Neural Network); DTW (Dynamic Time wrapping); Hidden Markov models; HMM (Hidden Markov Model); JPD (Joint Probability Distribution); LM (Language Model); LPCC (Linear Predictive Cepstral Coefficients); MFCC (Mel Frequency Cepstral Coefficients); MT (Machine Translation); PD (Punctuation Dictionary); PLP (Perceptual Linear Prediction Coefficient); QV (Quantization Vector); RV (Random Variables); SLT (Spoken Language Translation); Speech; Speech recognition; SVM (Support Vector Machine); Time series analysis; WER (Word Error Rate); Wrapping; WRR (Word Recognition Rate)
• DOI: 10.1109/SAI.2017.8252104

Speech processing is considered to be one of the most important application area of digital signal processing. Speech recognition and translation systems have consisted into two main systems, the first system represents an ASR system that contains two levels which are level one the feature extraction level As well as, level two the classification technique level using Data Time Wrapping (DTW), Hidden Markov Model (HMM), and Dynamic Bayesian Network (DBN). The second system is the Machine Translation (MT) system that mainly can be achieved by using three approaches which are (A) the statistical-based approach, (B) rule-approach, and (C) hybrid-based approach. In this study, we made a comparative study between classification techniques from ASR point of view, as well as, the translation approaches from MT point of view. The recognition rate was used in the ASR level and the error rate was used to evaluate the accuracy of the translated sentences. Furthermore, we classified the sample text audio files into four categories which were news, conversational, scientific phrases, and control categories.