End-to-End Speech Recognition from the Raw Waveform.
Neil ZeghidourNicolas UsunierGabriel SynnaeveRonan CollobertEmmanuel DupouxPublished in: INTERSPEECH (2018)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- language model
- speech synthesis
- speech signal
- pattern recognition
- automatic speech recognition
- noisy environments
- speech recognizer
- speech recognition technology
- multipath
- speaker independent
- speech processing
- congestion control
- frequency band
- frequency domain
- image compression
- speaker identification
- speaker adaptation
- video sequences
- information retrieval
- text localization and recognition
- motion estimation
- multiresolution
- multimedia