Neural HMMS Are All You Need (For High-Quality Attention-Free TTS).
Shivam MehtaÉva SzékelyJonas BeskowGustav Eje HenterPublished in: ICASSP (2022)
Keyphrases
- high quality
- hidden markov models
- network architecture
- neural network
- text to speech
- information systems
- low quality
- speech recognition
- image quality
- anomaly detection
- ground truth
- higher quality
- neural model
- selective attention
- super resolution
- high resolution
- case study
- bio inspired
- learning rules
- website
- speech synthesis
- artificial neural
- biological vision systems