Speech and Computer

This book constitutes the refereed proceedings of the 15th International Conference on Speech and Computer, SPECOM 2013, held in Pilsen, Czech Republic.
The 48 revised full papers presented were carefully reviewed and selected from 90 initial submissions. The papers are organized in topical sections on speech recognition and understanding, spoken language processing, spoken dialogue systems, speaker identification and diarization, speech forensics and security, language identification, text-to-speech systems, speech perception and speech disorders, multimodal analysis and synthesis, understanding of speech and text, and audio-visual speech processing.

Inhalt

Conference Papers.- Automatic Detection of the Prosodic Structures of Speech Utterances.- A Method for Auditory Evaluation of Synthesized Speech Intonation.- Acoustic Modeling with Deep Belief Networks for Russian Speech Recognition.- An Analysis of Speech Signals of the Choapam Variant Zapotec Language.- Analysis of Expert Manual Annotation of the Russian Spontaneous Monologue: Evidence from Sentence Boundary Detection.- Application of l1 Estimation of Gaussian Mixture Model Parameters for Language Identification.- Application of Automatic Fragmentation for the Semantic Comparison of Texts.- Auditory and Spectrographic Analysis of the Words of 2-8 Years-Old Russian Children.- Auditory and Visual Recognition of Emotional Behaviour of Foreign Language Subjects (by Native and Non-native Speakers.- Automatic Detection of Speech Disfluencies in the Spontaneous Russian Speech.- Automatic Morphological Annotation in a Text-to-Speech System for Hebrew.- Comparative Study of English, Dutch and German Prosodic Features (Fundamental Frequency and Intensity) as Means of Speech.- Covariance Matrix Enhancement Approach to Train Robust Gaussian Mixture Models of Speech Data.- Dealing with Diverse Data Variances in Factor Analysis Based Methods.- Detection of the Frequency Characteristics of the Articulation System with the Use of Voice Source Signal Recording Method.- Encoding of Spatial Perspectives in Human-Machine Interaction.- Evaluation of Advanced Language Modeling Techniques for Russian LVCSR.- Examining Vulnerability of Voice Verification Systems to Spoofing Attacks by Means of a TTS System.- Exploiting Multiple ASR Outputs for a Spoken Language Understanding Task.- Fast Algorithm for Automatic Alignment of Speech and Imperfect Text Data.- GMM Based Language Identification System Using Robust Features.- Hierarchical Clustering and Classification of Emotions in Human Speech Using Confusion Matrices.- Improvements in Czech Expressive Speech Synthesis in Limited Domain.- Improving Prosodic Break Detection in a Russian TTS System.- Investigation of Forensically Significant Changes of Acoustic Features with Regard to Code-Switching (on the Basis of Russian and German).- LIMA: A Spoken Language Identification Framework.- Language Identification System for the Tatar Language.- Language Model Comparison for Ukrainian Real-Time Speech Recognition System.- Lexicon Size and Language Model Order Optimization for Russian LVCSR.- Lingua-cognitive Survey of the Semantic Field "Aggression" in Multicultural Communication: Typed Text.- Method for Pornography Filtering in the WEB Based on Automatic Classification and Natural Language Processing.- Noise and Channel Normalized Cepstral Features for Far-speech Recognition.- Parametric Speech Synthesis and User Interface for Speech Modification.- Phrase-Final Segment Lengthening in Russian: Preliminary Results of a Corpus-Based Study.- Pseudo Real-Time Spoken Term Detection Using Pre-retrieval Results.- Results for Variable Speaker and Recording Conditions on Spoken IR in Finnish.- SVID Speaker Recognition System for NIST SRE 2012.- Segmentation of Telephone Speech Based on Speech and Non-speech Models.- Software for Assessing Voice Quality in Rehabilitation of Patients after Surgical Treatment of Cancer of Oral Cavity, Oropharynx and Upper Jaw.- Speaker Turn Detection Based on Multimodal Situation Analysis.- Speech and Crosstalk Detection for Robust Speech Recognition Using a Dual Microphone System.- Speech and Language Resources within Speech Recognition and Synthesis Systems for Serbian and Kindred South Slavic Languages.- Statistical Language Aspects of Intonation and Gender Features Based on the Lithuanian Language.- Text Understanding as Interpretation of Predicative Structure Strings of Main Text's Sentences as Result of Pragmatic Analysis (Combination of Linguistic and Statistic Approaches).- The Diarization System for an Unknown Number of Speakers.- The Problem of Voice Template Aging in Speaker Recognition Systems.- The Use of Several Language Models and Its Impact on Word Insertion Penalty in LVCSR.- The Use of d-gram Language Models for Speech Recognition in Russian.