Advances in speech and language technologies for Iberian languages : Second International Conference, IberSPEECH 2014, Las Palmas de Gran Canaria, Spain, November 19-21, 2014 : proceedings

This book constitutes the refereed proceedings of the IberSPEECH 2014 Conference, held in Las Palmas de Gran Canaria, Spain, in November 19-21, 2014. The 29 papers presented were carefully reviewed and selected from 60 submissions. The papers are organized in topical sections on speech production, analysis, coding and synthesis; speaker and language characterization; automatic speech recognition; speech of language technologies in different application fields. Front Matter....Pages - Analysis and Synthesis of Emotional Speech in Spanish for the Chat Domain....Pages 1-10 Developing a Basque TTS for the Navarro-Lapurdian Dialect....Pages 11-20 Fine Vocoder Tuning for HMM-Based Speech Synthesis: Effect of the Analysis Window Length....Pages 21-29 Quantitative Analysis of /l/ Production from RT-MRI: First Results....Pages 30-39 Statistical Text-to-Speech Synthesis of Spanish Subtitles....Pages 40-48 Unsupervised Accent Modeling for Language Identification....Pages 49-58 Global Speaker Clustering towards Optimal Stopping Criterion in Binary Key Speaker Diarization....Pages 59-68 Unsupervised Training of PLDA with Variational Bayes....Pages 69-78 On the Use of Convolutional Neural Networks in Pairwise Language Recognition....Pages 79-88 Global Impostor Selection for DBNs in Multi-session i-Vector Speaker Recognition....Pages 89-98 Phoneme-Lattice to Phoneme-Sequence Matching Algorithm Based on Dynamic Programming....Pages 99-108 Deep Maxout Networks Applied to Noise-Robust Speech Recognition....Pages 109-118 A Deep Neural Network Approach for Missing-Data Mask Estimation on Dual-Microphone Smartphones: Application to Noise-Robust Speech Recognition....Pages 119-128 Language Model Adaptation for Lecture Transcription by Document Retrieval....Pages 129-137 Articulatory Feature Extraction from Voice and Their Impact on Hybrid Acoustic Models....Pages 138-147 CVX-Optimized Beamforming and Vector Taylor Series Compensation with German ASR Employing Star-Shaped Microphone Array....Pages 148-157 Flexible Stand-Alone Keyword Recognition Application Using Dynamic Time Warping....Pages 158-167 Confidence Measures in Automatic Speech Recognition Systems for Error Detection in Restricted Domains....Pages 168-177 Recognition of Distant Voice Commands for Home Applications in Portuguese....Pages 178-188 Assessing the Applicability of Surface EMG to Tongue Gesture Detection....Pages 189-198 Towards Cross-Lingual Emotion Transplantation....Pages 199-208 A Preliminary Study of Acoustic Events Classification with Factor Analysis in Meeting Rooms....Pages 209-218 A Spoken Language Database for Research on Moderate Cognitive Impairment: Design and Preliminary Analysis....Pages 219-228 Towards Customized Automatic Segmentation of Subtitles....Pages 229-238 Bootstrapping a Portuguese WordNet from Galician, Spanish and English Wordnets....Pages 239-248 ATVS-CSLT-HCTLab System for NIST 2013 Open Keyword Search Evaluation....Pages 249-258 Speech Watermarking Based on Coding of the Harmonic Phase....Pages 259-268 The Translectures-UPV Toolkit....Pages 269-278 The AhoSR Automatic Speech Recognition System....Pages 279-288 Back Matter....Pages -