Adversarial attacks are a threat to automatic speech recognition (ASR)
s...
Automatic speech recognition (ASR) of multi-channel multi-speaker overla...
The ubiquitous presence of machine learning systems in our lives necessi...
We present PyChain, a fully parallelized PyTorch implementation of end-t...
Speaker diarization is an important pre-processing step for many speech
...
We present Espresso, an open-source, modular, extensible end-to-end neur...