Stutter-TTS: Controlled Synthesis and Improved Recognition of Stuttered Speech.
Xin ZhangIván Vallés-PérezAndreas StolckeChengzhu YuJasha DroppoOlabanji ShonibareRoberto Barra-ChicoteVenkatesh RavichandranPublished in: CoRR (2022)
Keyphrases
- text to speech
- recognition engine
- speech synthesis
- recognition rate
- speech corpus
- object recognition
- automatic speech recognition systems
- speech recognition
- recognition accuracy
- continuous speech recognition
- prosodic features
- neural network
- structural analysis
- digit recognition
- text recognition
- speech signal
- noisy environments
- recognition process
- automatic recognition
- activity recognition
- program synthesis
- speaker independent
- gait recognition
- probabilistic model
- speech sounds