Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech.
Cassia Valentini-BotinhaoJunichi YamagishiPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2018)
Keyphrases
- speech enhancement
- text to speech
- speech signal
- noisy environments
- speech synthesis
- speech recognition
- vocal tract
- speaker verification
- prosodic features
- automatic speech recognition
- background noise
- noisy speech
- speaker identification
- linear prediction
- hidden markov models
- text to speech synthesis
- noise reduction
- english text
- additive noise
- spectral analysis
- non stationary
- word processing
- acoustic features
- signal to noise ratio
- sound source
- frequency domain
- writing skills
- prior knowledge