Automatic Speech Recognition Using Probabilistic Transcriptions in Swahili, Amharic, and Dinka.
Amit DasPreethi JyothiMark Hasegawa-JohnsonPublished in: INTERSPEECH (2016)
Keyphrases
- automatic speech recognition
- broadcast news
- speech recognition
- data driven
- spoken document retrieval
- spontaneous speech
- probabilistic model
- spoken documents
- audio visual
- probabilistic logic
- context sensitive
- text to speech
- speech signal
- uncertain data
- fully automatic
- semi automatic
- generative model
- pattern recognition
- speech music discrimination
- gesture recognition
- emotion recognition
- data sets
- conditional probabilities
- bayesian networks