Papers by Krzysztof Marasek
Journal of Computers, 2016
Lecture Notes in Computer Science, 2015
Computerized Medical Imaging and Graphics, 2015
Machine translation is evolving quite rapidly in terms of quality. Nowadays, we have several mach... more Machine translation is evolving quite rapidly in terms of quality. Nowadays, we have several machine translation systems available in the web, which provide reasonable translations. However, these systems are not perfect, and their quality may decrease in some specific domains. This paper examines the effects of different training methods when it comes to Polish-English Statistical Machine Translation system used for the medical data. Numerous elements of the EMEA parallel text corpora and not related OPUS Open Subtitles project were used as the ground for creation of phrase tables and different language models including the development, tuning and testing of these translation systems. The BLEU, NIST, METEOR, and TER metrics have been used in order to evaluate the results of various systems. Our experiments deal with the systems that include POS tagging, factored phrase models, hierarchical models, syntactic taggers, and other alignment methods. We also executed a deep analysis of Polish data as preparatory work before automatized data processing such as true casing or punctuation normalization phase. Normalized metrics was used to compare results. Scores lower than 15% mean that Machine Translation engine is unable to provide satisfying quality, scores greater than 30% mean that translations should be understandable without problems and scores over 50 reflect adequate translations. The average results of Polish to English translations scores for BLEU, NIST, METEOR, and TER were relatively high and ranged from 7058 to 8272. The lowest score was 6438. The average results ranges for English to Polish translations were little lower (6758-7897). The real-life implementations of presented high quality Machine Translation Systems are anticipated in general medical practice and telemedicine.
We developed powerful unsupervised adaptation methods for speech recognition, i.e., the system im... more We developed powerful unsupervised adaptation methods for speech recognition, i.e., the system improves its performance while the user uses it. No prior enrollment phase is necessary where the speaker has to read a given text. We tried to further improve the unsupervised adaptation by using confidence measures. These give an estimate of how likely the recognized words were correct. Adaptation then only is conducted on utterances where the recognition result was reliable. This avoids the adaptation of wrong models in case of misrecognitions. As a confidence measure we use a set of features that comprise features related to phoneme durations, acoustic scores etc. These feature are collected during recognition and from the recognition result and a neural net is used as a classifier.
This paper describes a telephony-based automatic voice portal implemented in the Polish-Japanese ... more This paper describes a telephony-based automatic voice portal implemented in the Polish-Japanese Institute of Information Technology. The system is based on a single server with a Dialogic telephony voice board. It is integrated with the school's existing telephony network. The system uses Automatic Speech Recognition and Speech Synthesis to communicate with users. The dialog features: call routing, bulletin-board style information
Annual Conference of the International Speech Communication Association, 1993
The influence of word stress and the tense/lax vowels opposition on the phonation process in Germ... more The influence of word stress and the tense/lax vowels opposition on the phonation process in German was investigated. A set of stimulus words in which tense and lax vowels occurs in both stressed and unstressed position was read by ten speakers of German. The phonation behaviour was investigated using the electroglottographic signal (EGG) recorded by the Laryngograph. The EGG signal
![Francisco J. [Paco] Bethencourt Llobet](https://0.academia-photos.com/183598/45205/36833646/s200_francisco.bethencourt_llobet.jpg)
Uploads
Papers by Krzysztof Marasek