Please note that these pages are no longer up-to-date. The activities are now carried on in the HLT research unit (
DIalogo su TELefonO
We build speech recognizers for telephonic applications, with the main aim to include them in call-center systems (but not only). This means building acoustic and language models, and offering dialogue capabilities. 
At present we have a speech recognizer (have a look at the recording of a demo) with the following features: 
  • speaker independent (acoustic models are trained on several hundreds of speakers having good geographical coverage) 
  • Italian language 
  • continuous speech (no pauses between words) 
  • mixed initiative dialogue for limited domains (the user can provide information not explicitly asked by the system) 
  • recursive transition networks used to model the language (including bigrams, regular expressions, etc.)
  • We are presently working on:
    • barge-in capabilities (the user can speak during the vocal prompts)
    • dialogues on complex tasks (tourism)
    • verification / confidence scores for sentences and words
    • standard interfaces (C++ API, JavaSpeech) 
    • WEB access by voice (XML, VoxML languages) 
    • multimodal interaction 
    ITC links:
    ITC - Istituto Trentino di Cultura 
    ITCirst - Istituto per la Ricerca Scientifica e Tecnologica 
    SSI -Sistemi Sensoriali Interattivi 
    Other stuffs:
  • People involved in the project
  • Brief history of telephone speech recognition at ITCirst
  • Systems and applications:
  • Italy Direct - 170
  • Caritro
  • Dialogue
  • Collected speech databases:
  • Reports
  • Project management (internal use only)
  • Other projects concerning speech recognition at IRST
  • MUNST (MUltilingual Natural Speech Technology)
  • SHINE (SpeecH Interaction in Noisy Environment)
  • Tools
  • A morphological analyzer for the Italian language
  • TRAMORPH (morphological tool)
  • ILE (Italian LExicon), a 588,000 word lexicon
    Last update march 2, 2000 
    Maintainer Roberto Gretter