Subject: Re: [AUDITORY] Comparison ASH/HSR; ChiME From: Laszlo Toth <tothl@xxxxxxxx> Date: Tue, 14 Feb 2017 08:52:52 +0100 List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>On Mon, 13 Feb 2017, Levity wrote: > (a) What are the most recent significant results comparing human and > machine speech recognition capabilities? At the latest Interspeech conference there were a couple of papers stating that machine speech recognition capabilities are now very close to that of humans. I was very interested to see these talks, and I was very disappointed when it turned out that they cited the same old paper of Lippmann regarding the human side. So there seems to be no newer paper that measures human performance, or if there is, the speech recognition community is not aware of it. Laszlo Toth Hungarian Academy of Sciences * Research Group on Artificial Intelligence * "Failure only begins e-mail: tothl@xxxxxxxx * when you stop trying" http://www.inf.u-szeged.hu/~tothl *