Statistical Language and Speech Processing

1. Front Matter

   PDF

2. Invited Talks

   1. Deep Learning of Representations: Looking Forward

      • Yoshua Bengio

      Pages 1-37

   2. Challenges and Opportunities of Multilingual Information Access

      • Christof Monz

      Pages 38-38

3. Regular Papers

   1. Unsupervised Rhyme Scheme Identification in Hip Hop Lyrics Using Hidden Markov Models

      • Karteek Addanki, Dekai Wu

      Pages 39-50

   2. Complementarity of Lexical Cohesion and Speaker Role Information for Story Segmentation of French TV Broadcast News

      • Abdessalam Bouchekif, Géraldine Damnati, Delphine Charlet

      Pages 51-61

   3. An Investigation of Single-Pass ASR System Combination for Spoken Language Understanding

      • Fethi Bougares, Mickael Rouvier, Nathalie Camelin, Paul Deléglise, Yannick Estève

      Pages 62-70

   4. Predicting Part-of-Speech Tags and Morpho-Syntactic Relations Using Similarity-Based Technique

      • Samuel W. K. Chan, Mickey M. C. Chong

      Pages 71-82

   5. Statistical Error Correction Methods for Domain-Specific ASR Systems

      • Horia Cucu, Andi Buzo, Laurent Besacier, Corneliu Burileanu

      Pages 83-92

   6. Reward Shaping for Statistical Optimisation of Dialogue Management

      • Layla El Asri, Romain Laroche, Olivier Pietquin

      Pages 93-101

   7. Discriminative Framework for Spoken Tunisian Dialect Understanding

      • Marwa Graja, Maher Jaoua, Lamia Hadrich Belguith

      Pages 102-110

   8. Finding the Most Likely Upper Level State Sequence for Hierarchical HMMs

      • Akira Hayashi, Kazunori Iwata, Nobuo Suematsu

      Pages 111-122

   9. Generalization of Discriminative Approaches for Speech Language Understanding in a Multilingual Context

      • Bassam Jabaian, Fabrice Lefèvre, Laurent Besacier

      Pages 123-134

   10. Speech/Music Discrimination via Energy Density Analysis

       • Stanisław Kacprzak, Mariusz Ziółko

       Pages 135-142

   11. Histogram Equalization Using Centroids of Fuzzy C-Means of Background Speakers’ Utterances for Speaker Identification

       • Myung-Jae Kim, Il-Ho Yang, Ha-Jin Yu

       Pages 143-151

   12. Unsupervised Segmentation for Different Types of Morphological Processes Using Multiple Sequence Alignment

       • Amit Kirschenbaum

       Pages 152-163

   13. Cross-Lingual Random Indexing for Information Retrieval

       • Hans Moen, Erwin Marsi

       Pages 164-175

   14. Rational Kernels for Arabic Text Classification

       • Attia Nehar, Djelloul Ziadi, Hadda Cherroun

       Pages 176-187

   15. Experiments with Semantic Similarity Measures Based on LDA and LSA

       • Nobal Niraula, Rajendra Banjade, Dan Ştefănescu, Vasile Rus

       Pages 188-199

   16. MDL-Based Models for Transliteration Generation

       • Javad Nouri, Lidia Pivovarova, Roman Yangarber

       Pages 200-211

   17. Using Regression for Spectral Estimation of HMMs

       • Jordan Rodu, Dean P. Foster, Weichen Wu, Lyle H. Ungar

       Pages 212-223

This book constitutes the refereed proceedings of the First International Conference on Statistical Language and Speech Processing, SLSP 2013, held in Tarragona, Spain, in July 2013. The 24 full papers presented together with two invited talks were carefully reviewed and selected from 61 submissions. The papers cover a wide range of topics in the fields of computational language and speech processing and the statistical methods that are currently in use.

• hidden Markov models
• machine learning
• sentiment analysis
• similarity
• statistical methods

• Research Group on Mathematical Linguistics, Universitat Rovira i Virgili, Tarragona, Spain

  Adrian-Horia Dediu, Carlos Martín-Vide

• Research Institute for Information and Language Processing, Research Group in Computational Linguistics, University of Wolverhampton, Wolverhampton, UK

  Ruslan Mitkov

• Fakultät für Informatik, Institut für Wissens- und Sprachverarbeitung, Otto-von-Guericke-Universität Magdeburg, Magdeburg, Germany

  Bianca Truthe

Policies and ethics