Encoder Transfer for Attention-based Acoustic-to-word Speech Recognition.
Sei UenoTakafumi MoriyaMasato MimuraShinsuke SakaiYusuke ShinoharaYoshikazu YamaguchiYushi AonoTatsuya KawaharaPublished in: INTERSPEECH (2018)
Keyphrases
- speech recognition systems
- speech recognition
- speech recognizers
- speech recognizer
- hidden markov models
- wall street journal corpus
- speaker independent
- speech processing
- language model
- speech signal
- pattern recognition
- automatic speech recognition
- speech synthesis
- acoustic models
- speech recognition technology
- word error rate
- keyword spotting
- bit rate
- noisy speech
- handwriting recognition
- speaker identification
- noisy environments
- speaker dependent
- speaker recognition
- isolated word