Global RNN Transducer Models For Multi-dialect Speech Recognition.
Takashi FukudaSamuel ThomasMasayuki SuzukiGakuto KurataGeorge SaonBrian KingsburyPublished in: INTERSPEECH (2022)
Keyphrases
- speech recognition
- speech synthesis
- speech signal
- hidden markov models
- automatic speech recognition
- pattern recognition
- speech recognition technology
- acoustic models
- noisy environments
- language model
- speech processing
- speech recognition systems
- handwriting recognition
- speech recognizer
- recurrent neural networks
- keyword spotting
- edge detection
- speech retrieval
- probabilistic model