Automatic Speech Recognition with Stuttering Speech Removal using Long Short-Term Memory (LSTM)
S.Girirajan1, R.Sangeetha2, T.Preethi3, A.Chinnappa4
1S.Girirajan*, Department of Computer Science and Engineering, SRM Institute of Science and Technologyy, Kattankulathur, India.
2R.Sangeetha, Department of Computer Science and Engineering, SRM Institute of Science and Technologyy, Kattankulathur, India.
3T.Preethi, Department of Computer Science and Engineering, SRM Institute of Science and Technologyy, Kattankulathur, India.
4A.Chinnappa, Department of Computer Science and Engineering, SRM Institute of Science and Technologyy, Kattankulathur, India.
Manuscript received on January 02, 2020. | Revised Manuscript received on January 15, 2020. | Manuscript published on January 30, 2020. | PP: 1677-1681 | Volume-8 Issue-5, January 2020. | Retrieval Number: E6230018520/2020©BEIESP | DOI: 10.35940/ijrte.E6230.018520
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Stuttering or Stammering is a speech defect within which sounds, syllables, or words are rehashed or delayed, disrupting the traditional flow of speech. Stuttering can make it hard to speak with other individuals, which regularly have an effect on an individual’s quality of life. Automatic Speech Recognition (ASR) system is a technology that converts audio speech signal into corresponding text. Presently ASR systems play a major role in controlling or providing inputs to the various applications. Such an ASR system and Machine Translation Application suffers a lot due to stuttering (speech dysfluency). Dysfluencies will affect the phrase consciousness accuracy of an ASR, with the aid of increasing word addition, substitution and dismissal rates. In this work we focused on detecting and removing the prolongation, silent pauses and repetition to generate proper text sequence for the given stuttered speech signal. The stuttered speech recognition consists of two stages namely classification using LSTM and testing in ASR. The major phases of classification system are Re-sampling, Segmentation, Pre-Emphasis, Epoch Extraction and Classification. The current work is carried out in UCLASS Stuttering dataset using MATLAB with 4% to 6% increase in accuracy when compare with ANN and SVM.
Keywords: ASR, Dysfluency, Repetition, Prolongation, LSTM, MFCC Feature Extraction.
Scope of the Article: Signal and Speech Processing.