Speech waveform synthesis from MFCC sequences with generative adversarial networks.
Lauri JuvelaBajibabu BollepalliXin WangHirokazu KameokaManu AiraksinenJunichi YamagishiPaavo AlkuPublished in: CoRR (2018)
Keyphrases
- speech recognition
- speech signal
- hidden markov models
- speaker identification
- speaker recognition
- generative model
- automatic speech recognition
- multi agent
- fundamental frequency
- speaker diarization
- speech synthesis
- network structure
- multi modal
- social networks
- audio visual
- sequential patterns
- speech recognition systems
- dialogue system
- noisy environments
- frequency domain
- acoustic features
- classification accuracy
- pattern recognition