Special issue on Advances in Deep Learning Based Speech Processing
摘要截稿:
全文截稿: 2020-03-30
影响因子: 5.535
期刊难度:
CCF分类: B类
中科院JCR分区:
• 大类 : 计算机科学 - 2区
• 小类 : 计算机:人工智能 - 2区
• 小类 : 神经科学 - 2区
Overview
Deep learning has triggered a big revolution inon speech processing. The revolution started from the successful application of deep neural networks to automatic speech recognition, and was quickly spread to other topics of speech processing, including speech analysis, speech denoising and separation, speaker and language recognition, speech synthesis, and spoken language understanding. Such This tremendous success is achieved by the long-term evolutionadvances of neural network technologies as well as the big explosion of speech data and fast development of computing power.
Although such a bigDespite this tremendous success has been made, deep learning based speech processing still has many challenges for real-world wide deployment. For example, when the distance between a speaker and a microphone array is larger than 10 meters, the word error rate of a speech recognizer may be as high as overis typically less than 50%; end-to-end deep learning based speech processing systems have shown potential advantages over hybrid systems, however, they still have a high requirement ofto large-scale labelled speech data; deep learning based speech synthesis has been highly competitive with human-sounding speech and much better than to traditional methods, however, the models are not stable, lacks controllability and are still too large and slow to be able to deployedput into mobile and IoT devices, etc.
AccordinglyTherefore, new theoretical methods in deep learning and speech processing are required needed to tackle the above challenges, as well as to yield novel insights into new directions and applicationproblems.
This special issue on recent advances of deep learning based speech processing invitesaims to accelerate research progress by providing a forum for researchers and practitioners to present novel their latest contributions that advance addressing theoretical and practical aspects of deep learning related speech processing techniques. The special issue will feature a collection of high quality theoretical articles with novel new insights and creative solutions to the key research challenges, as well asand state-of-the-art speech processing algorithms/systems that demonstrate highly-competitive performance with potential industrial impacts. The technologies addressing emerging problems and directions are also very welcome.
Topics of interest for this special issue include, but are not limited to: