Audio style transfer using shallow convolutional networks and random filters
| Autor: | Huihuang Zhao, Gaobo Yang, Manimaran Ramasamy, Jiyou Chen |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer Networks and Communications
Computer science Speech recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 020207 software engineering 02 engineering and technology Convolutional neural network Image (mathematics) Tone (musical instrument) Continuous wavelet Hardware and Architecture Transfer (computing) 0202 electrical engineering electronic engineering information engineering Media Technology Spectrogram Sound quality Representation (mathematics) Software |
| Zdroj: | Multimedia Tools and Applications. 79:15043-15057 |
| ISSN: | 1573-7721 1380-7501 |
| DOI: | 10.1007/s11042-020-08798-6 |
| Popis: | Recently, with the advent of Convolutional Neural Network (CNN) era, Neural style transfer on images has become a very active research topic and the style of an image can be transferred to another image through a CNN so that the image retains both its own content and another style of image. In this work, we propose an algorithm for audio style transfer that uses the force of CNN to generate a new audio from a style audio. We use Continuous Wavelet Transfer(CWT) to convert the audio into a spectrogram and then use the spectrogram as the representation of the audio image through image style transfer method to obtain a new image, and finally, generate an audio using iterative phase reconstruction with Griffin-Lim. We succeed in transferring audio such as light music but had difficulty in transferring audio that has lyrics and high-level metrics such as emotion or tone. We propose several measures to improve the quality of audio and a lot of experimental results shows that our method is better than other methods in terms of sound quality. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink