Konuşma Tanıma için Bir Evrimsel Sinir Ağı Modeli Uygulaması

Konuşma tanıma, bir cihazın fonetik bir dilde kelime bilgisi ile diksiyonu analiz etme ve bunları makinenin anlaşılır bir düzenine dönüştürebilme kabiliyetidir. Konuşmayı anlayan ve metne dönüştüren süreç ve teknikleri oluşturan disiplinlerarası bir dilbilim olup bilgisayar bilimi ve elektrik mühendisliği alt alanıdır. Bu çalışmada konuşma verilerinin tanınması için evri bir sinir ağı modeli sunulmaktadır.

Anahtar Kelimeler:

Konuşma Tanıma, Derin Öğrenme, Karışıklık Matrisi

A Convolutional Neural Network Model Implementation for Speech Recognition

Speech recognition is the capability of an appliance to analyze vocable and diction in a phonetic language and turn them into a machine comprehensible arrangement. It is an interdisciplinary subfield of linguistics, computer science and electrical engineering that establishes processes and techniques that understands and converts speech to text. This paper presents a convolutional neural network model for recognition of speech data.

Keywords:

Speech Recognition, Deep Learning, Confusion Matrix,

PDF

___

[1] K. Davis , R. Biddulph, and S. Balashek “Automatic Recognition of Spoken Digits”, The Journal of the Acoustical Society of America, vol. 24, no. 6 , pp. 637-642, 1952.
[2] S. Das, M. A. Picheny, In Automatic Speech and Speaker Recognition, Boston, USA: Springer, 1996, pp. 457-479
[3] S. Hochreiter, J. Schmidhuber, “Long short-term memory”, Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997
[4] M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean and M. Kudlur “Tensorflow: A System for large-scale machine learning”, 12th Symposium on Operating Systems Design and Implementation (OSDI), Savannah, GA, USA, 2016, pp. 265-283 [5] Tensowflow Speech Commands Data Set v0.01 (2019, 01 April). [Online]. Erişim: https://www.kaggle.com/c/tensorflow-speech-recognition-challenge/data
[6] H. Nyquist, “Certain topics in telegraph transmission theory”, Transactions of the American Institute of Electrical Engineers, vol. 47, no. 2, pp. 617-644, 1928
[7] Davis, Steven, and P. Mermelstein, “Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences”, IEEE transactions on acoustics, speech, and signal processing, vol. 28, no. 4, pp. 357-366, 1980
[8] Slaney, Malcolm, Michele Covell, and B. Lassiter, “Automatic audio morphing”, International Conference on Acoustics, Speech, and Signal Processing Conference (IEEE), 1996, pp. 1001-1004
[9] S. Postalcioglu, “Performance Analysis of Different Optimizers for Deep Learning-Based Image Recognition”, International Journal of Pattern Recognition and Artificial Intelligence, 2019
[10] Townsend, T. James “Theoretical analysis of an alphabetic confusion matrix”, Perception & Psychophysics, vol. 9, no. 1, pp. 40-50, 1971