AHUMADA: a large speech corpus in Spanish for speaker identification and verification.
Javier Ortega-GarciaJoaquín González-RodríguezVictoria Marrero-AguiarJuan J. Díaz-GómezRamon Garcia-JimenezJose Juan Lucena-MolinaJosé A. G. Sanchez-MoleroPublished in: ICASSP (1998)
Keyphrases
- speaker identification
- speech corpus
- language identification
- automatic speech recognition
- speech recognition
- speech synthesis
- speech signal
- broadcast news
- noisy environments
- gaussian mixture model
- spoken document retrieval
- speaker dependent
- hidden markov models
- feature extraction
- language model
- question answering
- pattern recognition
- audio features
- keywords
- out of vocabulary
- non stationary