The Recognition of Persian Phonemes Using PPNet

سال انتشار: 1399
نوع سند: مقاله ژورنالی
زبان: انگلیسی
مشاهده: 141

فایل این مقاله در 8 صفحه با فرمت PDF قابل دریافت می باشد

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

JR_JMSI-10-2_003

تاریخ نمایه سازی: 28 تیر 1402

چکیده مقاله:

Background: In this paper, a novel approach is proposed for the recognition of Persian phonemes in the Persian consonant‑vowel combination (PCVC) speech dataset. Nowadays, deep neural networks (NNs) play a crucial role in classification tasks. However, the best results in speech recognition are not yet as perfect as human recognition rate. Deep learning techniques show outstanding performance over many other classification tasks, such as image classification and document classification. Furthermore, the performance is sometimes better than a human. The reason why automatic speech recognition systems are not as qualified as the human speech recognition system, mostly depends on features of data which are fed to deep NNs. Methods: In this research, first, the sound samples are cut for the exact extraction of phoneme sounds in ۵۰ ms samples. Then, phonemes are divided into ۳۰ groups, containing ۲۳ consonants, ۶ vowels, and a silence phoneme. Results: The short‑time Fourier transform is conducted on them, and the results are given to PPNet (a new deep convolutional NN architecture) classifier and a total average of ۷۵.۸۷% accuracy is reached which is the best result ever compared to other algorithms on separated Persian phonemes (like in PCVC speech dataset). Conclusion: This method not only can be used for recognizing mono‑phonemes but it can also be adopted as an input to the selection of the best words in speech transcription

نویسندگان

Saber Malekzadeh

Department of Electrical Engineering, Vali‑e‑Asr University of Rafsanjan, Rafsanjan- Khazar University, Baku, Azerbaijan

Mohammad Hossein Gholizadeh

Department of Electrical Engineering, Vali‑e‑Asr University of Rafsanjan, Rafsanjan

Seyed Naser Razavi

Department of Computer Engineering, University of Tabriz, Tabriz, Iran

Hossein Ghayoumi Zadeh

Department of Electrical Engineering, Vali‑e‑Asr University of Rafsanjan, Rafsanjan