One of the most difficult speech recognition tasks is accurate recognition of human to human communication. Advances in deep learning over the last few years have produced major speech recognition improvements on the representative Switchboard conversational corpus. Word error rates that just a few years ago were 14% have dropped to 8.0%, then 6.6% and most recently 5.8%, and are now believed to be within striking range of human performance. This then raises two issues -what IS human performance, and how far down can we still drive speech recognition error rates? A recent paper by Microsoft suggests that we have already achieved human performance. In trying to verify this statement, we performed an independent set of human performance measurements on two conversational tasks and found that human performance may be considerably better than what was earlier reported, giving the community a significantly harder goal to achieve. We also report on our own efforts in this area, presenting a set of acoustic and language modeling techniques that lowered the word error rate of our own English conversational telephone LVCSR system to the level of 5.5%/10.3% on the Switchboard/CallHome subsets of the Hub5 2000 evaluation, which -at least at the writing of this paper -is a new performance milestone (albeit not at what we measure to be human performance!). On the acoustic side, we use a score fusion of three models: one LSTM with multiple feature inputs, a second LSTM trained with speaker-adversarial multitask learning and a third residual net (ResNet) with 25 convolutional layers and time-dilated convolutions. On the language modeling side, we use word and character LSTMs and convolutional WaveNet-style language models.

SUMMARYRNA-binding proteins Lin28a/b regulate cellular growth and tissue regeneration. Here, we investigated the role of Lin28 in the control of axon regeneration in postmitotic neurons. We find that Lin28a/b are both necessary and sufficient for supporting axon regeneration in mature sensory neurons through their regulatory partners, let-7 microRNAs (miRNAs). More importantly, overexpression of Lin28a in mature retinal ganglion cells (RGCs) produces robust and sustained optic nerve regeneration. Additionally, combined overexpression of Lin28a and downregulation of Pten in RGCs act additively to promote optic nerve regeneration, potentially by reducing the backward turning of regenerating RGC axons. Our findings not only reveal a vital role of Lin28 signaling in regulating mammalian axon regeneration but also identify a signaling pathway that can promote axon regeneration in the central nervous system (CNS).

No abstract

No abstract