Speech and Computer

This book constitutes the refereed proceedings of the 16th International Conference on Speech and Computer, SPECOM 2014, held in Novi Sad, Serbia.
The 56 revised full papers presented together with 3 invited talks were carefully reviewed and selected from 100 initial submissions. It is a conference with long tradition that attracts researchers in the area of computer speech processing (recognition, synthesis, understanding etc.) and related domains (including signal processing, language and text processing, multi-modal speech processing or human-computer interaction for instance).

Inhalt

Invited Talks.- Creating Expressive TTS Voices for Conversation Agent Applications.- Gaps to Bridge in Speech Technology.- Instantaneous Harmonic Analysis: Techniques and Applications to Speech Signal Processing.- Conference Papers.- A Comparison of Two Prosody Modelling Approaches for Sesotho and Serbian.- A Dependency Treebank for Serbian: Initial Experiments.- A Framework for Recording Audio-Visual Speech Corpora with a Microphone and a High-Speed Camera.- A Neural Network Keyword Search System for Telephone Speech.- A Note on Feature Extraction Based on Kanade-Shi-Tomasi Procedure and Kalman Filters.- A Robust SVM/GMM Classifier for Speaker Verification.- A Sequence Training Method for Deep Rectifier Neural Networks in Speech Recognition.- Algorithms for Acceleration of Image Processing at Automatic Registration of Meeting Participants.- Analysis and Synthesis of Glottalization Phenomena in German- Accented English.- Annotation and Personality: Individual Differences in Sentence Boundary Detection.- Associative Mechanism of Foreign Spoken Language Perception (Forensic Phonetic Aspect).- Automatic Alignment of Phonetic Transcriptions for Russian.- Automatic Post-Editing Method Using Translation Knowledge Based on Intuitive Common Parts Continuum for Statistical Machine Translation.- Automatic Stop List Generation for Clustering Recognition Results of Call Center Recordings.- Blur Estimation Methods for System of Audiovisual Monitoring of Meeting Participants.- Controlling the Uncertainty Area in the Real Time LVCSR Application.- Convolutional Neural Network for Refinement of Speaker Adaptation Transformation.- Corpus-Based Regiolect Studies: Kazan Region.- Crowdsourcing Interactive Technology for Natural-Technical Objects Integrated Monitoring.- Dramatic Piece Reader and it's Evaluation by the Blind and Sighted Assessors.- Estimating Stochasticity of Acoustic Signals.- Exploiting Non-negative Matrix Factorization with Linear Constraints in Noise-Robust Speaker Identification.- Extraction of Features for Lip-reading Using Autoencoders.- F0 Declination Patterns in Russian.- Filled Pauses and Lengthenings Detection Based on the Acoustic Features for the Spontaneous Russian Speech.- First Experiments with Relevant Documents Selection for Blind Relevance Feedback in Spoken Document Retrieval.- How Speech Technologies Can Help People with Disabilities.- HTK-Based Recognition of Whispered Speech.- Human Resources Management in Conditions of Operators' Psychophysiological State Changes.- Impact of Emotional Speech to Automatic Speaker Recognition - Experiments on GEES Speech Database.- Improving Speech Synthesis Quality for Voices Created from an Audiobook Database.- «INFANT.MAVS» - Multimedia Model for Infants Cognitive and Emotional Development Study.- Influence of Agent Behaviour on Human-Virtual Agent Body Interaction.- Modeling of Process Dynamics by Sequence of Homogenous Semantic Networks on the Base of Text Corpus Sequence Analysis.- New Method of Speech Signals Adaptive Features Construction Based on the Wavelet-like Transform and Support Vector Machines.- On a Hybrid NN/HMM Speech Recognition System with a RNN-Based Language Model.- On Principles of Annotated Databases of the Semantic Field "Aggression".- On the Possibility of the Skype Channel Speaker Identification (on the Basis of Acoustic Parameters).- Parametric Representation of Kazakh Gestural Speech.- Personified Voice Interaction Software in Billing Systems.- Phrase-Final Lengthening in Russian: Pre-boundary or Pre-pausal?.- Proportional-Integral-Derivative Control of Automatic Speech Recognition Speed.- Quality Assessment of HMM-Based Speech Synthesis Using Acoustical Vowel Analysis.- Quality Improvements of Zero-Concatenation-Cost Chain Based Unit Selection.- Robust Multi-Band ASR Using Deep Neural Nets and Spectro-temporal Features.- Semantic Entity Detection in the Spoken Air Traffic Control Data.- Simplified Simultaneous Perturbation Stochastic Approximation for the Optimization of Free Decoding Parameters.- Speaker Detection Using Phoneme Specific Hidden Markov Models.- Speaking Rate Estimation Based on Deep Neural Networks.- Speech Rhythmic Patterns of the Slavic Languages.- State Level Control for Acoustic Model Training.- Structural Model and Behavior Scenarios of Information Navigation Mobile Robot .- Study of Morphological Factors of Factored Language Models for Russian ASR.- The Use of Speech Technology in Computer Assisted Language Learning Systems.- Using Random Forests for Prosodic Break Prediction Based on Automatic Speech Labeling.- Vulnerability of Voice Verification Systems to Spoofing Attacks by TTS Voices Based on Automatically Labeled Telephone Speech.