@inproceedings{Campr-TSD-2013,
  IS = { zkontrolovano 25 Jan 2014 },
  UPDATE  = { 2014-01-06 },
author={Campr, Pavel and Pra{\v z}{\' a}k, Ale{\v s} and Psutka, Josef V. and Psutka, Josef},
title={Online Speaker Adaptation of an Acoustic Model Using Face Recognition},
year={2013},
month={September},
pages={378-385},
editor={Habernal, Ivan and Matou{\v s}ek, V{\' a}clav},
booktitle={Text, Speech, and Dialogue: 16th International Conference, TSD 2013},
publisher={Springer},
address={Heidelberg, Germany},
isbn={978-3-642-40584-6},
volume={8082},
series={Lecture Notes in Computer Science},
keywords={acoustic model; face recognition; speaker adaptation; multimodal processing; automatic speech recognition},
annote={We have proposed and evaluated a novel approach for online speaker adaptation of an acoustic model based on face recognition. Instead of traditionally used audio-based speaker identification we investigated video modality for the task of speaker detection. A simulated on-line transcription created by a Large-Vocabulary Continuous Speech Recognition (LVCSR) system for online subtitling is evaluated utilizing speaker independent acoustic models, gender dependent models and models of particular speakers. In the experiment, the speaker dependent acoustic models were trained offline, and are switched online based on the decision of the face recognizer, which reduced Word Error Rate (WER) by 12% relatively compared to speaker independent baseline system.},
doi={10.1007/978-3-642-40585-3_48},
url={http://dx.doi.org/10.1007/978-3-642-40585-3_48},
project={GACR P103/12/G084},
venue = {Pilsen, Czech Republic},
month = {September},
day = {1--5},
psurl={http://www.kky.zcu.cz/cs/publications/1/CamprPavel_2013_OnlineSpeaker.pdf},
book_pages={601},
}