Publication Details
TRAP based features for LVCSR of meeting data
Grézl František, Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
Speech recognition, TRAP, LVCSR
This paper describes using temporal patterns (TRAPs) feature extraction in large vocabulary continuous speech recognition (LVCSR) of meeting data. Frequency differentiation and local operators are applied to critical-band speech spectrum. Tests are performed with HMM recognizer on ICSI meetings database. We show that TRAP features in combination with standard ones lead to improvement of word-error rate (WER).
This paper describes using temporal patterns (TRAPs) feature extraction in large vocabulary continuous speech recognition (LVCSR) of meeting data. Frequency differentiation and local operators are applied to critical-band speech spectrum. Tests are performed with HMM recognizer on ICSI meetings database. We show that TRAP features in combination with standard ones lead to improvement of word-error rate (WER).
@INPROCEEDINGS{FITPUB7485, author = "Martin Karafi\'{a}t and Franti\v{s}ek Gr\'{e}zl and Jan \v{C}ernock\'{y}", title = "TRAP based features for LVCSR of meeting data", pages = "437--440", booktitle = "Proc. 8th International Conference on Spoken Language Processing", journal = "8th International Conference on Spoken Language Processing", volume = 2004, number = 10, year = 2004, location = "Jeju Island, KR", publisher = "Sunjin Printing Co,", ISSN = "1225-4111", language = "english", url = "https://www.fit.vut.cz/research/publication/7485" }