Tunisian Dialectal End-to-end Speech Recognition based on DeepSpeech.
Abir MessaoudiHatem HaddadChayma FouratiMoez Ben Haj HmidaAymen Ben Elhaj MabroukMohamed GraietPublished in: ACLING (2021)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- speech recognizer
- pattern recognition
- speech processing
- speech recognition technology
- language model
- speech synthesis
- speech signal
- automatic speech recognition
- congestion control
- speech recognition systems
- speaker identification
- noisy environments
- speaker dependent
- speech retrieval
- speaker independent
- isolated word
- neural network
- text localization and recognition
- speaker adaptation
- signal processing
- information retrieval