Journal Information
Speech Communication
Impact Factor:

Call For Papers
Speech Communication is an interdisciplinary journal whose primary objective is to fulfil the need for the rapid dissemination and thorough discussion of basic and applied research results. In order to establish frameworks to inter-relate results from the various areas of the field, emphasis will be placed on viewpoints and topics of a transdisciplinary nature. The editorial policy and the technical content of the Journal are the responsibility of the Editors and the Institutional Representatives. The Institutional Representatives assist the Editors in the definition and the control of editorial policy as well as in maintaining connections with scientific associations, international congresses and regional events. The Editorial Board contributes towards the gathering of material for publication and assists the Editors in the editorial process.

Editorial Policy:
The journal's primary objectives are:
• to present a forum for the advancement of human and human-machine speech communication science;
• to stimulate cross-fertilization between different fields of this domain;
• to contribute towards the rapid and wide diffusion of scientifically sound contributions in this domain.

Subject Coverage:
Subject areas covered in this journal include:
• Basics of oral communication and dialogue: modelling of production and perception processes; phonetics and phonology; syntax; semantics and pragmatics of speech communication; cognitive aspects.
• Models and tools for language learning: functional organisation and developmental models of human language capabilities; acquisition and rehabilitation of spoken language; speech & hearing defects and aids.
• Speech signal processing: analysis, coding, transmission, enhancement, robustness to noise.
• Models for automatic speech communication: speech recognition; language identification; speaker recognition; speech synthesis; oral dialogue.
• Development and evaluation tools: monolingual and multilingual databases; assessment methodologies; specialised hardware and software packages; field experiments; market development.
• Multimodal human computer interface: using speech I/O in combination with other modalities, e.g., gesture and handwriting.
• Forensic speech science: forensic voice comparison; forensic analysis of disputed utterances; speaker identification by earwitnesses.
Last updated by Dou Sun in 2016-12-16
Special Issues
Special Issue on Realism in Robust Speech and Language Processing
Submission Date: 2017-03-31

How can you be sure that your research has actual impact in real-world applications? This is one of the major challenges currently faced in many areas of speech processing, with the migration of laboratory solutions to real-world applications, which is what we address by the term "Realism". Real application scenarios involve several acoustic, speaker and language variabilities which challenge the robustness of systems. As early evaluations in practical targeted scenarios are hardly feasible, many developments are actually based on simulated data, which leaves concerns for the viability of these solutions in real-world environments. Simulated datasets are not usually acoustically realistic. For example, many popular datasets obtained by mixing speech and noise at fixed signal-to-noise ratios include some levels and types of distortion that never happen in real life. Most also ignore Lombard effect which occurs as noise levels increase. Even real datasets are often not ecologically realistic because they were not collected in the real conditions of use. This can result in satisfactory performance of the tested methods on scenarios that will never happen in practice, while their performance may be much worse in real scenarios. Furthermore, complex and expensive methods might be obtained that are actually not required. Thus, a suitable dataset for a given task will be strongly depend on how well it matches the acoustic characteristics of the target application scenarios. Found data is easy to locate from different available online sources such as YouTube, among others. However the knowledge of the context, identity, acoustic variability and mismatch with specific system goals may cause such data to be less effective. Even, well organized speech data from data resource consortia such as LDC used for different purposes than they were originally collected for, may in fact be constructing irrelevant solutions. For example, the big amount of spontaneous telephone conversations included in NIST-SRE datasets, which have been considered as the standard corpora for speaker recognition, would be unrealistic in access control applications, considering the speech duration and modality. New advancements in machine learning technologies for speech and language, such as Deep Neural Networks (DNN), require extensive datasets and researchers are increasingly moving towards found data with less knowledge or understanding of the impact this has on final solutions.
Last updated by Dou Sun in 2016-12-16
Related Publications
Related Journals
CCFFull NameImpact FactorPublisherISSN
cIET Communications0.624IET1751-8628
bAI Communications0.837IOS Press0921-7126
China Communications0.424China Communications Magazine, Co., Ltd.1673-5447
cComputer Communications2.099ELSEVIER0140-3664
IEEE Wireless Communications4.148IEEE1536-1284
aIEEE Journal on Selected Areas in Communications3.435IEEE0733-8716
Procedia - Social and Behavioral Sciences ELSEVIER1877-0428
IEICE Transactions on Communications IEICE
Communications in Mobile Computing Springer2192-1121
Full NameImpact FactorPublisher
IET Communications0.624IET
AI Communications0.837IOS Press
China Communications0.424China Communications Magazine, Co., Ltd.
Computer Communications2.099ELSEVIER
IEEE Wireless Communications4.148IEEE
IEEE Journal on Selected Areas in Communications3.435IEEE
Procedia - Social and Behavioral Sciences ELSEVIER
IEICE Transactions on Communications IEICE
Communications in Mobile Computing Springer
Related Conferences
CCFCOREQUALISShortFull NameSubmissionNotificationConference
SMARTCOMPInternational Conference on Smart Computing 2017-02-032017-03-272017-05-29
ConTELInternational Conference on Telecommunications2013-03-082013-04-192013-06-26
ICICTInternational Conference on Computational Intelligence and Communication Technology2015-09-152015-10-152016-02-12
baa2NOSSDAVInternational Workshop on Network and Operating Systems Support for Digital Audio and Video2017-02-242017-04-142017-06-20
ITSTInternational Conference on ITS Telecommunications2017-01-142017-03-012017-05-29
FITInternational Conference on Frontiers of Information Technology2016-07-312016-09-202016-12-19
aa*a1INFOCOMInternational Conference on Computer Communications2016-07-222016-11-252017-05-01
baa1MobiHocInternational Symposium on Mobile Ad Hoc Networking and Computing2017-01-132017-04-012017-07-10
CompArchFederated Events on Component-Based Software Engineering and Software Architecture2016-01-112016-02-152016-04-05
MONAMIInternational Conference on Mobile Networks and Management2015-05-082015-07-062015-09-16