INTERSPEECH 2004 - ICSLP
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 with standard ones lead to improvement of word-error rate (WER).
Bibliographic reference. Grezl, Frantisek / Karafiat, Martin / Cernocky, Jan (2004): "TRAP based features for LVCSR of meting data", In INTERSPEECH-2004, 437-440.