Subject: [AUDITORY] CFP: Special Issue on Advances in Deep Learning Based Speech Processing From: DeLiang Wang <dwang@xxxxxxxx> Date: Fri, 6 Mar 2020 14:26:02 -0500 List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>Neural Networks Special issue Call for Papers: *Advances in Deep Learning Based Speech Processing * https://www.journals.elsevier.com/neural-networks/call-for-papers/advance= s-in-deep-learning=20 * * *Deadline: June 30, 2020* Deep learning has triggered a revolution in speech processing. The=20 revolution started from the successful application of deep neural=20 networks to automatic speech recognition, and quickly spread to other=20 topics of speech processing, including speech analysis, speech denoising=20 and separation, speaker and language recognition, speech synthesis, and=20 spoken language understanding. This tremendous success has been achieved=20 thanks to the advances in neural network technologies as well as the=20 explosion of speech data and fast development of computing power. Despite this success, deep learning based speech processing still faces=20 many challenges for real-world wide deployment. For example, when the=20 distance between a speaker and a microphone array is larger than 10=20 meters, the word error rate of a speech recognizer may be as high as=20 over 50%; end-to-end deep learning based speech processing systems have=20 shown potential advantages over hybrid systems, however, they require=20 large-scale labelled speech data; deep learning based speech synthesis=20 has been highly competitive with human-sounding speech and much better=20 than traditional methods, however, the models are not stable, lack=20 controllability and are still too large and slow to be deployed onto=20 mobile and IoT devices. Therefore, new methods and algorithms in deep learning and speech=20 processing are needed to tackle the above challenges, as well as to=20 yield novel insights into new directions and applications. This special issue aims to accelerate research progress by providing a=20 forum for researchers and practitioners to present their latest=20 contributions that advance theoretical and practical aspects of deep=20 learning based speech processing techniques. The special issue will=20 feature theoretical articles with novel new insights, creative solutions=20 to key research challenges, and state-of-the-art speech processing=20 algorithms/systems that demonstrate competitive performance with=20 potential industrial impacts. The ideas addressing emerging problems and=20 directions are also welcome. *Topics of interest* for this special issue include, but are not limited=20 to: *=C2=A0=C2=A0 Speaker separation *=C2=A0=C2=A0 Speech denoising *=C2=A0=C2=A0 Speech recognition *=C2=A0=C2=A0 Speaker and language recognition *=C2=A0=C2=A0 Speech synthesis * =C2=A0 Audio and speech analysis * =C2=A0 Multimodal speech processing *Submission instructions: * Prospective authors should follow the standard author instructions for=20 Neural Networks, and submit manuscripts online at=20 https://www.editorialmanager.com/neunet/default.aspx=20 <https://urldefense.com/v3/__https://www.editorialmanager.com/neunet/defa= ult.aspx__;!!KGKeukY!hyw14JfC_4VzymjJoHB5DKVZlDryYvR-avb5pEOk0U0nWB7HJqhd= mcBfaCz5UYwN9lnTRA$>. Authors should select "VSI: Speech Based on DL" when they reach the=20 "Article Type" step and the "Request Editor" step in the submission proce= ss. *Important dates: * June 30, 2020 - Submission deadline September 30, 2020 - First decision notification November 30, 2020 - Revised version deadline December 31, 2020 - Final decision notification March, 2021 - Publication *Guest Editors: * Xiao-Lei Zhang, Northwestern Polytechnical University, China Lei Xie, Northwestern Polytechnical University, China Eric Fosler-Lussier, Ohio State University, USA Emmanuel Vincent, Inria, France