Multi-speaker Sequence-to-sequence Speech Synthesis for Data Augmentation in Acoustic-to-word Speech Recognition.
Sei UenoMasato MimuraShinsuke SakaiTatsuya KawaharaPublished in: ICASSP (2019)
Keyphrases
- speech recognition
- speech synthesis
- prosodic features
- speech recognition systems
- speech recognizer
- hidden markov models
- speech recognizers
- text to speech
- speech processing
- speech signal
- automatic speech recognition
- pattern recognition
- noisy environments
- acoustic models
- language model
- speech recognition technology
- speaker recognition
- speaker identification
- speech retrieval
- data mining
- isolated word
- wall street journal corpus