SpecSwap: A Simple Data Augmentation Method for End-to-End Speech Recognition
Xingchen Song, Zhiyong Wu, Yiheng Huang, Dan Su, Helen Meng
Topics & Concepts
End-to-end principleComputer scienceSpeech recognitionSimple (philosophy)Artificial intelligencePhilosophyEpistemologySpeech Recognition and SynthesisSpeech and Audio ProcessingMusic and Audio Processing