![]() Each segment was combined by taking the fast Fourier transform. For this purpose, sound signals were first segmented to their state before normalization. To take advantage of the convolutional neural networks’ ability to characterize two-dimensional signals, spectrogram image features that visualize the speech signal frequency distribution were used. Moreover, converting audio signals into images in the most appropriate way is critical for a convolutional neural network, a deep learning model commonly used in image applications. ![]() While there is still no generally accepted feature set, the selection of handcrafted features is a challenging task. Many different acoustic features were used in the studies. In this study, regional accents of British English were recognized for both gender-independent and gender-dependent experiments using a convolutional neural network. However, the recognition of a language's regional accents is still a challenging problem. Numerous studies have been carried out using various languages to improve the performance of accent recognition systems. Accent recognition is a significant area of research, whose importance has increased in recent years.
0 Comments
Leave a Reply. |