DeepA: A Deep Neural Analyzer For Speech And Singing Vocoding.
Sergey NikonorovBerrak SismanMingyang ZhangHaizhou LiPublished in: CoRR (2021)
Keyphrases
- network architecture
- audio features
- neural network
- acoustic features
- speech recognition
- speech synthesis
- audio visual
- speech signal
- recognition engine
- text to speech
- language acquisition
- music information retrieval
- text to speech synthesis
- broadcast news
- neural model
- artificial neural networks
- speech processing
- dialogue system
- fitted q iteration
- endpoint detection
- audio stream
- multi stream
- bio inspired
- speaker identification
- automatic speech recognition
- data sets
- english text
- high speed
- biologically plausible
- hidden markov models
- learning rules
- artificial intelligence
- automatic speech recognition systems