Machine Learning - Audio and Speech
🔢Data
data-science
machine-learning
A speech system has two parts
- Sound to word
- Language model: Immer nächstes Wort vorhersagen.
Literature
- Breakthroughs in Speech Recognition Achieved with the Use of Transformers
-
Comparing End-To-End Speech Recognition Architectures in 2021
- Comparing Listen Attend and Spell (LAS), and Recurrent Neural Network Transducers (RNNT) as technologies.
- Review Article from 2015
Discuss on Twitter ● Improve this article: Edit on GitHub