Signal Processing Platforms and Algorithms for Real-Life ...downloads.hindawi.com/journals/jece/2017/2913236.pdfSignal Processing Platforms and Algorithms for Real-Life Communications

EditorialSignal Processing Platforms and Algorithms for Real-LifeCommunications and Listening to Digital Audio

Alexander Petrovsky,1 WanggenWan,2 Manuel Rosa-Zurera,3 and Alexey Karpov4

1Belarusian State University of Informatics and Radioelectronics, Minsk, Belarus2Shanghai University, Shanghai, China3University of Alcala, Madrid, Spain4St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, St. Petersburg, Russia

Correspondence should be addressed to Alexander Petrovsky; [email protected]

Received 2 April 2017; Accepted 2 April 2017; Published 19 July 2017

Copyright © 2017 Alexander Petrovsky et al. This is an open access article distributed under the Creative Commons AttributionLicense, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properlycited.

Design of modern electronic communication systemsinvolves diversified scientific areas including algorithms,architectures, and hardware development. Variety of existentmultimedia devices gives rise to development of platform-dependent signal processing algorithms. Their integrationinto existent digital environment is an urgent problem forapplication engineers. Considering a wide range of applica-tions including hearing aids, real-life communications, andlistening to digital audio, the following research areas are ofparticular importance: advanced time-frequency representa-tions, audio user interfaces, audio and speech enhancement,assisted listening, and perception and phonation modeling.

This special issue aims at publishing papers presentingnovel methodologies and techniques (including theoreticalmethods, algorithms, and software) correspondent to theseresearch areas. It includes high-quality papers dealing withapplications in speech recognition, emotion recognition inspeech signals, or informed source separation in orchestralrecordings. The problems addressed in the accepted papersare among the top trends in the signal processing andcommunications research community.

Human interaction with computers through voice-userinterfaces is the issue one of the papers deals with. It isbased on Automatic Speech Recognition, and nowadays theobjective is to solve the problemof spontaneous speech recog-nition. Spontaneous speech is characterized by hesitations,disfluencies, and changes that convey information about the

speaker.Thepaper “Experiments onDetection ofVoicedHes-itations inRussian Spontaneous Speech,” byV.Verkhodanovaand V. Shapranov, addresses the issue of voiced hesitations(filled pauses and sound lengthenings) detection in Russianspontaneous speech by utilizing different machine learningtechniques: from grid search and gradient descent in rule-based approaches to such data-driven ones as ELM andSVM based on the automatically extracted acoustic features.Experimental results on themixed and quality diverse corpusof spontaneous Russian speech indicate the efficiency of thetechniques for the task in question, with SVM outperformingother methods.

The need for understanding business trends, ensuringpublic security, and improving the quality of customer servicehas caused a sustained development of speech analyticssystems which transform speech data into a measurableand searchable index of words, phrases, and paralinguisticmarkers. Keyword spotting technology makes a substantialpart of such systems. In the article entitled “A RussianKeyword Spotting System Based on Large Vocabulary Con-tinuous Speech Recognition and Linguistic Knowledge” byV. Smirnov et al., the authors present an automatic systemfor keyword spotting in continuous speech. This systemuses high-level linguistic knowledge and models for Russianspeech and language; it has been implemented as softwareand applied in real-life telecommunication tasks for continu-ous speech processing.

HindawiJournal of Electrical and Computer EngineeringVolume 2017, Article ID 2913236, 2 pageshttps://doi.org/10.1155/2017/2913236

https://doi.org/10.1155/2017/2913236

2 Journal of Electrical and Computer Engineering

In recent years, more attention is paid to the study ofemotion recognition. Speech, as one of the most importantways of communication in human daily life, contains richemotional information. Speech emotion recognition becauseof its wide application significance and research value inintelligence and naturalness of human-computer interactionaspects has gotmore andmore attention from the researchersin recent years. The authors Z. Cairong et al. of the article“A Novel DBN Feature Fusion Model for Cross-CorpusSpeech Emotion Recognition” present an automatic systemfor speaker emotion recognition by speech analysis. Thissystem uses Deep Belief Nets for feature fusion and selection;it has been studied in cross-corpus experiments for emotionrecognition tasks using emotional Chinese and Germanspeech databases.

Speech intelligibility and speech recognition are impor-tant and trending topics of research in various fields ofscience: Linguistics, Medicine, Electrical Engineering, andInformationTechnology. Speech recognition process is inves-tigated from different sides, as only an integrated approachcould lead to a better understanding of this process. Oneof these research areas is intelligibility improvement ofsynthesized speech in noise, which has demanded muchattention in recent years. In the article entitled “Crosslin-guistic Intelligibility of Russian and German Speech inNoisy Environment” by R. Potapova and M. Grigorieva, theauthors present quantitative results of experimental researchon speech perception and intelligibility of spoken utterancesand words by different listeners in various noisy conditions.Multiple experiments have been made using Russian andGerman speech data with addition of white and pink acousticnoises with different intensity and signal-to-noise ratios.

Audio source-separation is also a challenging task whenwe have sources corresponding to different instrument sec-tions, which are strongly correlated in time and frequency.Without any previous knowledge, it is difficult to separate twosections which play, for instance, consonant notes simultane-ously. One way to tackle this problem is to introduce into theseparation framework information about the characteristicsof the signals, such as a well-aligned score. The paperentitled “Score-Informed Source Separation forMultichannelOrchestral Recordings” by M. Miron et al. proposes andevaluates a system for score-informed audio source separa-tion for multichannel orchestral recordings.The given articleaims at adapting and extending score-informed audio sourceseparation to the inherent complexity of orchestral music.This scenario involves not only challenges, like changesin dynamics and tempo, a large variety of instruments,high reverberance, and simultaneous melodic lines, but alsoopportunities as multichannel recordings. Results show thatit is possible to align the original score with the audio of theperformance and separate the sources corresponding to theinstrument sections. In addition, authors derive applications,which allow for multiperspective audio enhancement, asacoustic scene rendering, and integrate them into an onlinerepository which allows the distribution of the generatedaudio content.

Acknowledgments

We thank all the authors who made submissions to thisspecial issue and the reviewers for their support and detailedreviews in making this special issue possible.

Alexander PetrovskyWanggen Wan

Manuel Rosa-ZureraAlexey Karpov

RoboticsJournal of

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014


Active and Passive Electronic Components

Control Scienceand Engineering

Journal of


International Journal of

RotatingMachinery


Hindawi Publishing Corporation http://www.hindawi.com

Journal of

Volume 201

Submit your manuscripts athttps://www.hindawi.com

VLSI Design



Shock and Vibration


Civil EngineeringAdvances in

Acoustics and VibrationAdvances in



Electrical and Computer Engineering

Journal of

Advances inOptoElectronics

Hindawi Publishing Corporation http://www.hindawi.com

Volume 2014

The Scientific World JournalHindawi Publishing Corporation http://www.hindawi.com Volume 2014

SensorsJournal of


Modelling & Simulation in EngineeringHindawi Publishing Corporation http://www.hindawi.com Volume 2014


Chemical EngineeringInternational Journal of Antennas and

Propagation




Navigation and Observation



DistributedSensor Networks


Documents

Signal Processing Platforms and Algorithms for Real-Life ...downloads.hindawi.com/journals/jece/2017/2913236.pdfSignal Processing Platforms and Algorithms for Real-Life Communications