Multilingual acoustic models for speech recognition and synthesis.
Siegfried KunzmannVolker FischerJorge GonzalezOssama EmamCarsten GüntherEric JankePublished in: ICASSP (3) (2004)
Keyphrases
- speech recognition
- acoustic models
- speech recognizer
- automatic speech recognition
- speaker independent
- hidden markov models
- language model
- speech signal
- pattern recognition
- cross lingual
- speech recognition systems
- broadcast news
- speaker identification
- cross language
- cross language information retrieval
- multimedia
- multi modal
- face recognition