Journal of Artificial Intelligence and Data Mining، جلد ۱۳، شماره ۳، صفحات ۳۳۷-۳۴۵
عنوان فارسی
چکیده فارسی مقاله
کلیدواژه‌های فارسی مقاله
عنوان انگلیسی Robust Persian Digit Recognition in Noisy Environments Using Hybrid CNN-BiGRU Model
چکیده انگلیسی مقاله Artificial intelligence (AI) has significantly advanced speech recognition applications. However, many existing neural network-based methods struggle with noise, reducing accuracy in real-world environments. This study addresses isolated spoken Persian digit recognition (zero to nine) under noisy conditions, particularly for phonetically similar numbers. A hybrid model combining residual convolutional neural networks and bidirectional gated recurrent units (BiGRU) is proposed, utilizing word units instead of phoneme units for speaker-independent recognition. The FARSDIGIT1 dataset, augmented with various approaches, is processed using Mel-Frequency Cepstral Coefficients (MFCC) for feature extraction. Experimental results demonstrate the model’s effectiveness, achieving 98.53%, 96.10%, and 95.92% accuracy on training, validation, and test sets, respectively. In noisy conditions, the proposed approach improves recognition by 26.88% over phoneme unit-based LSTM models and surpasses the Mel-scale Two Dimension Root Cepstrum Coefficients (MTDRCC) feature extraction technique along with MLP model (MTDRCC+MLP) by 7.61%.
کلیدواژه‌های انگلیسی مقاله Spoken Digit Recognition,data augmentation,Convolutional neural network,Bidirectional Gated Recurrent Unit
نویسندگان مقاله Ali Nasr-Esfahani |
Department of Electrical and Computer Engineering, Qom University of Technology, Iran.

Mehdi Bekrani |
Department of Electrical and Computer Engineering, Qom University of Technology, Iran.

Roozbeh Rajabi |
Department of Electrical and Computer Engineering, Qom University of Technology, Iran.

نشانی اینترنتی https://jad.shahroodut.ac.ir/article_3523_f201bc6609c5a5f37a19acc4c5ba8d5b.pdf
فایل مقاله فایلی برای مقاله ذخیره نشده است
کد مقاله (doi)
زبان مقاله منتشر شده en
موضوعات مقاله منتشر شده
نوع مقاله منتشر شده
برگشت به: صفحه اول پایگاه   |   نسخه مرتبط   |   نشریه مرتبط   |   فهرست نشریات