Advances in Speech and Language Technologies for Iberian Languages

1. Front Matter

   PDF

2. Speech Production, Analysis, Coding and Synthesis

   1. Analysis and Synthesis of Emotional Speech in Spanish for the Chat Domain

      • Yesika Laplaza, Juan María Garrido

      Pages 1-10

   2. Developing a Basque TTS for the Navarro-Lapurdian Dialect

      • Eva Navas, Inma Hernaez, Daniel Erro, Jasone Salaberria, Beñat Oyharçabal, Manuel Padilla

      Pages 11-20

   3. Fine Vocoder Tuning for HMM-Based Speech Synthesis: Effect of the Analysis Window Length

      • Agustin Alonso, Daniel Erro, Eva Navas, Inma Hernaez

      Pages 21-29

   4. Quantitative Analysis of /l/ Production from RT-MRI: First Results

      • Samuel Silva, Paula Martins, Catarina Oliveira, António Teixeira

      Pages 30-39

   5. Statistical Text-to-Speech Synthesis of Spanish Subtitles

      • S. Piqueras, M. A. del-Agua, A. Giménez, J. Civera, A. Juan

      Pages 40-48

3. Speaker and Language Characterization

   1. Unsupervised Accent Modeling for Language Identification

      • David Martínez González, Jesús Villalba López, Eduardo Lleida Solano, Alfonso Ortega Gimenez

      Pages 49-58

   2. Global Speaker Clustering towards Optimal Stopping Criterion in Binary Key Speaker Diarization

      • Héctor Delgado, Xavier Anguera, Corinne Fredouille, Javier Serrano

      Pages 59-68

   3. Unsupervised Training of PLDA with Variational Bayes

      • Jesús Villalba, Eduardo Lleida

      Pages 69-78

   4. On the Use of Convolutional Neural Networks in Pairwise Language Recognition

      • Alicia Lozano-Diez, Javier Gonzalez-Dominguez, Ruben Zazo, Daniel Ramos, Joaquin Gonzalez-Rodriguez

      Pages 79-88

   5. Global Impostor Selection for DBNs in Multi-session i-Vector Speaker Recognition

      • Omid Ghahabi, Javier Hernando

      Pages 89-98

4. Automatic Speech Recognition

   1. Phoneme-Lattice to Phoneme-Sequence Matching Algorithm Based on Dynamic Programming

      • Ciro Gracia, Xavier Anguera, Jordi Luque, Ittai Artzi

      Pages 99-108

   2. Deep Maxout Networks Applied to Noise-Robust Speech Recognition

      • F. de-la-Calle-Silos, A. Gallardo-Antolín, C. Peláez-Moreno

      Pages 109-118

   3. A Deep Neural Network Approach for Missing-Data Mask Estimation on Dual-Microphone Smartphones: Application to Noise-Robust Speech Recognition

      • Iván López-Espejo, José A. González, Ángel M. Gómez, Antonio M. Peinado

      Pages 119-128

   4. Language Model Adaptation for Lecture Transcription by Document Retrieval

      • A Martínez-Villaronga, M. A del Agua, J. A Silvestre-Cerdà, J Andrés-Ferrer, A Juan

      Pages 129-137

   5. Articulatory Feature Extraction from Voice and Their Impact on Hybrid Acoustic Models

      • Jorge Lombart, Antonio Miguel, Eduardo Lleida

      Pages 138-147

   6. CVX-Optimized Beamforming and Vector Taylor Series Compensation with German ASR Employing Star-Shaped Microphone Array

      • Juan A. Morales-Cordovilla, Hannes Pessentheiner, Martin Hagmüller, José A. González, Gernot Kubin

      Pages 148-157

   7. Flexible Stand-Alone Keyword Recognition Application Using Dynamic Time Warping

      • Miquel Ferrarons, Xavier Anguera, Jordi Luque

      Pages 158-167

   8. Confidence Measures in Automatic Speech Recognition Systems for Error Detection in Restricted Domains

      • Julia Olcoz, Alfonso Ortega, Antonio Miguel, Eduardo Lleida

      Pages 168-177

   9. Recognition of Distant Voice Commands for Home Applications in Portuguese

      • Miguel Matos, Alberto Abad, Ramón Astudillo, Isabel Trancoso

      Pages 178-188

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.

• Automatic speech recognition
• Speaker and language characterization
• data hiding
• deep learning
• document retrieval
• hybrid models
• information retrieval
• knowledge acquisition
• language model adaption
• machine learning
• moderate cognitive impairment
• neural networks
• noise robustness
• speech analysis
• speech and language technologies
• speech coding
• speech production
• speech synthesis
• text-to-speech synthesis
• video lectures

• ETSIT, Las Palmas de Gran Canaria, Spain

  Juan Luis Navarro Mesa, Eduardo Hernández Pérez, Pedro Quintana Morales, Antonio Ravelo García, Iván Guerra Moreno

• University of Zaragoza, Spain

  Alfonso Ortega

• Dep. of Electronics, Telecommunications and Informatics Engineering, University of Aveiro, Portugal

  António Teixeira

• ATVS Biometric Recognition Group,, Universidad Autónoma de Madrid, Spain

  Doroteo T. Toledano

Policies and ethics