Please be scientific



所有跟贴·加跟贴·新语丝读书论坛http://www.xys.org/cgi-bin/mainpage.pl

送交者: articsyn 于 2006-1-30, 18:11:36:

回答: 两全其美网网友对自动化所徐波语音识别造假事件评论 由 IronBull 于 2006-1-16, 08:49:23:


I've been working in speech recognition for several
years. Now I'm focusing on other aspects of speech
processing. If anyone here has reviewed the literature
on speech recognition from 1970's, you'll find "95%" accuracy rate could often be achieved UNDER CERTAIN
TEST CONDITIONS. To my understanding, the accracy rate range is highly dependent on the task, and only
comparible among the systems that joined the test.

Here is an example link in "《新清华》2002年9月27日":
http://news.cic.tsinghua.edu.cn/xqh/xqhnews/read.php?id=4170
Please notice the numbers "93.7%" and "98.7%".
If you don't understand the test conditions, the
numbers are nonsense to you.

I have studied in Tsinghua and the Institute of
Automation, and worked in IBM's speech lab. My
previous and I colleagues had never looked down upon
any researchers in other local teams. To those who
blindly pre-assumed the technique of speech resognition
in a local institute MUST be worse than that of
oversea labs, I really disrespect them :(

Maybe people dislike the news style in CCTV. But
it's useless to suspect everything and do nothing
constructive. It's even harmful to conclude without
any background research and knowledge. If anyone
here really care about a scientific evaluation,
please go to study and compare the 863-evaluation procedure with the NIST one. If you find something
can be improved, that's a real academic contribution!





所有跟贴:


加跟贴

笔名: 密码(可选项): 注册笔名请按这里

标题:

内容(可选项):

URL(可选项):
URL标题(可选项):
图像(可选项):


所有跟贴·加跟贴·新语丝读书论坛http://www.xys.org/cgi-bin/mainpage.pl