SpeeD @ SpeD 2013

Between 16 and 19 October 2013, most of the SpeeD group participated at The 7th International Conference on Speech Technology and Human-Computer Dialogue “SpeD 2013”, which was held in Cluj-Napoca, Romania, where they presented several research studies related to automatic speech recognition, spoken term detection, speech synthesis, speaker recognition and time delay estimation:

  • Text Spotting in Large Speech Databases for Under-Resourced Languages;
  • Multilingual Query by Example Spoken Term Detection for Under-Resourced Languages;
  • Statistically Augmented Preprocessing/Normalization Module for a Romanian Text-to-Speech System;
  • On Forensic Speaker Recognition Case Pre-Assessment;
  • Extensive Evaluation Experiments for the Accumulated Cross-Power Spectrum Methods for Time Delay Estimation.