Projects

Multimodal Interaction

Technologies to deal with a recent paradigm shift in the design of Pattern Recognition systems, where the traditional concept of full-automation is being changed to human-feedback conditioned decision processes. Problems and applications considered within this area include: Relevance-based (image) information retrieval and Interactive-Predictive processing for Computer Assited Machine Translation, as well as for the Interactive Transcription of speech audio streems and text image Documents.

Machine Translation

Speech-to-speech translation or text-to-text translation for limited domains. Finite-state and statistical transducers are used as the basis of the machine translation systems. These models can be learnt automatically from real examples of translation. Applications: translation of technical reports, hotel services, etc.

Handwritten Text Recognition

Recognition of handwritten text. Hidden Markov models are employed at the backend of this technology after preprocessing and feature extraction from line images. Applications: extraction of electronically readable text from handwritten documents, such as forms, surveys, historical old documents, etc.

Image Analysis and Computer Vision

General Statistical and Syntactic Pattern Recognition techniques for image analysis and recognition. Some applications: OCR and document analysis, medical diagnosis, biometric identification, image and video retrieval.

Automatic Speech Recognition and Understanding

The speech utterances are decoded into strings of words or into strings of semantic units. Finite-state grammars are used as the basis of such systems. These finite-state grammars are learnt automatically from real examples of utterances or text. Applications: telephone exchange services, device control by voice, information queries, etc.