Voice Conversion for Stuttered Speech, Instruments, Unseen Languages and Textually Described Voices.
Matthew BaasHerman KamperPublished in: CoRR (2023)
Keyphrases
- text to speech
- multi lingual
- spoken language
- speech quality
- emotion recognition
- voice activity detection
- english text
- speech synthesis
- speech recognition errors
- speech recognition
- fundamental frequency
- speech signal
- speech sounds
- language independent
- noisy environments
- previously unseen
- speaker identification
- text summarization
- expressive power
- language identification
- synthesized speech
- endpoint detection
- male and female
- text to speech synthesis
- cross lingual
- audio visual
- information retrieval
- databases
- packet loss
- vocal tract
- broadcast news
- query translation
- automatic speech recognition
- speaker recognition