Phonetically Induced Subwords for End-to-End Speech Recognition.
Vasileios PapadourakisMarkus MüllerJing LiuAthanasios MouchtarisMaurizio OmologoPublished in: Interspeech (2021)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- language model
- speech processing
- speech synthesis
- speech recognition technology
- speech signal
- congestion control
- automatic speech recognition
- pattern recognition
- speech recognizer
- noisy environments
- speaker identification
- speech recognizers
- speaker independent
- computer vision
- machine learning
- coding scheme
- speech retrieval
- real world