@article{article_710749, title={Investigation of the Effect of LSTM Hyperparameters on Speech Recognition Performance}, journal={Avrupa Bilim ve Teknoloji Dergisi}, pages={161–168}, year={2020}, DOI={10.31590/ejosat.araconf21}, author={Dokuz, Yeşim and Tüfekci, Zekeriya}, keywords={Ses tanıma,Derin Öğrenme,RNN,LSTM,LSTM hiperparametreleri}, abstract={With the recent advances in hardware technologies and computational methods, computers became more powerful for analyzing difficult tasks, such as speech recognition and image processing. Speech recognition is the task of extraction of text representation of a speech signal using computational or analytical methods. Speech recognition is a challenging problem due to variations in accents and languages, powerful hardware requirements, big dataset needs for generating accurate models, and environmental factors that affect signal quality. Recently, with the increasing processing ability of hardware devices, such as Graphical Processing Units, deep learning methods became more prevalent and state-of-the-art method for speech recognition, especially Recurrent Neural Networks (RNNs) and Long-Short Term Memory (LSTMs) networks which is a variant of RNNs. In the literature, RNNs and LSTMs are used for speech recognition and the applications of speech recognition with various parameters, i.e. number of layers, number of hidden units, and batch size. It is not investigated that how the parameter values of the literature are selected and whether these values could be used in future studies. In this study, we investigated the effect of LSTMs hyperparameters on speech recognition performance in terms of error rates and deep architecture cost. Each parameter is investigated separately while other parameters remain constant and the effect of each parameter is observed on a speech corpus. Experimental results show that each parameter has its specific values for the selected number of training instances to provide lower error rates and better speech recognition performance. It is shown in this study that before selecting appropriate values for each LSTM parameters, there should be several experiments performed on the speech corpus to find the most eligible value for each parameter.}, publisher={Osman SAĞDIÇ}