Detail výsledku

Towards Lower Error Rates in Phoneme Recognition

SCHWARZ, P., MATĚJKA, P., ČERNOCKÝ, J. Towards Lower Error Rates in Phoneme Recognition. Lecture Notes in Computer Science, 2004, vol. 2004, no. 3206, 8 p. ISSN: 0302-9743.
Typ
článek v časopise
Jazyk
anglicky
Autoři
Schwarz Petr, Ing., Ph.D., UPGM (FIT)
Matějka Pavel, Ing., Ph.D., UPGM (FIT)
Černocký Jan, prof. Dr. Ing., UPGM (FIT)
Abstrakt

We investigate techniques for acoustic modeling in automatic recognition of context-independent phoneme strings from the TIMIT database. The baseline phoneme recognizer is based on TempoRAl Patterns (TRAP). This recognizer is simplified to shorten processing times and reduce computational requirements. More states per phoneme and bi-gram language models are incorporated into the system and evaluated. The question of insufficient amount of training data is discussed and the system is improved. All modifications lead to a faster system with about 23.6% relative improvement over the baseline in phoneme error rate.

Klíčová slova

phoneme recognition, traps, speech recognition, feature extraction

URL
Rok
2004
Strany
8
Časopis
Lecture Notes in Computer Science, roč. 2004, č. 3206, ISSN 0302-9743
Kniha
Lecture Notes in Computer Science
Vydavatel
Springer
Místo
Spolková republika Německo
BibTeX 
@article{BUT45379,
  author="Petr {Schwarz} and Pavel {Matějka} and Jan {Černocký}",
  title="Towards Lower Error Rates in Phoneme Recognition",
  journal="Lecture Notes in Computer Science",
  year="2004",
  volume="2004",
  number="3206",
  pages="8",
  issn="0302-9743",
  url="http://www.springerlink.com/index/KBY35VBXY16WHV56"
}
Projekty
Hlasové technologie v podpoře informační společnosti, GAČR, Standardní projekty, GA102/02/0124, zahájení: 2002-01-01, ukončení: 2004-12-31, ukončen
Multi Modal Meeting Manager, IST-2001-34485, zahájení: 2002-03-01, ukončení: 2005-02-28, ukončen
Pracoviště
Ústav počítačové grafiky a multimédií (UPGM)
Ústav radioelektroniky (UREL)
Nahoru