-
Upload Video
videos in mp4/mov/flv
close
Upload video
Note: publisher must agree to add uploaded document -
Upload Slides
slides or other attachment
close
Upload Slides
Note: publisher must agree to add uploaded document -
Feedback
help us improve
close
Feedback
Please help us improve your experience by sending us a comment, question or concern
Please help transcribe this video using our simple transcription tool. You need to be logged in to do so.
Description
Many machine learning tasks can be ex- pressed as the transformationor transduc- tion of input sequences into output se- quences: speech recognition, machine trans- lation, protein secondary structure prediction and text-to-speech to name but a few. One of the key challenges in sequence transduction is
learning to represent both the input and output sequences in a way that is invariant to sequential distortions such as shrinking, stretching and translating. Recurrent neu- ral networks (RNNs) are a powerful sequence learning architecture that has proven capa- ble of learning such representations. How- ever RNNs
traditionally require a pre-defined alignment between the input and output se- quences to perform transduction. This is a severe limitation since finding the alignment is the most difficult aspect of many sequence transduction problems. Indeed, even deter- mining the length of the output sequence is often
challenging. This paper introduces an end-to-end, probabilistic sequence transduc- tion system, based entirely on RNNs, that re- turns a distribution over output sequences of all possible lengths and alignments for any in- put sequence. Experimental results are pro- vided on the TIMIT speech corpus.