TransFusion: Transcribing Speech with Multinomial Diffusion.
Matthew BaasKevin EloffHerman KamperPublished in: CoRR (2022)
Keyphrases
- speech recognition
- anisotropic diffusion
- text classification
- diffusion process
- speech signal
- probabilistic model
- recognition engine
- speech synthesis
- text categorization
- logit model
- diffusion processes
- speaker recognition
- spoken dialogue systems
- information diffusion
- broadcast news
- nonlinear diffusion
- diffusion model
- language acquisition
- automatic speech recognition
- naive bayes
- em algorithm
- information retrieval
- emotion recognition
- noisy environments
- machine learning
- spoken language
- speaker identification
- audio visual
- fisher information
- expectation maximization
- maximum likelihood