TransFusion: Transcribing Speech with Multinomial Diffusion.
Matthew BaasKevin EloffHerman KamperPublished in: SACAIR (2022)
Keyphrases
- speech recognition
- anisotropic diffusion
- speech signal
- speech synthesis
- audio visual
- diffusion process
- text categorization
- recognition engine
- text classification
- naive bayes
- broadcast news
- automatic speech recognition
- probabilistic model
- information diffusion
- spoken language
- speaker identification
- text to speech
- maximum likelihood
- discrete data
- gaussian mixture model
- spoken dialogue systems
- diffusion processes
- social networks
- logit model
- hearing impaired