https://medium.com/@harisankarh
Nice to read. I didn't guess that the article would be so fun to read and insightful. I wouldn't have even read it if it wasn't ranked 1 in hackernews.
The authors propose an unsupervised encoder for ASR. The encoder is trained using an interesting upstream task of predicting whether an audio portion or clip succeeds the current one or not. The authors report superior…
Nice to read. I didn't guess that the article would be so fun to read and insightful. I wouldn't have even read it if it wasn't ranked 1 in hackernews.
The authors propose an unsupervised encoder for ASR. The encoder is trained using an interesting upstream task of predicting whether an audio portion or clip succeeds the current one or not. The authors report superior…