Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
woodson
on March 11, 2017
|
parent
|
context
|
favorite
| on:
Reaching new records in speech recognition
For anyone wondering what the recordings in the HUB5 2000 eval data (the test data) sound like:
https://catalog.ldc.upenn.edu/desc/addenda/LDC2002S09.wav
joshgel
on March 12, 2017
[–]
God. Transcribing that would be mind-numbing. Glad computers are getting better at this.
Consider applying for YC's W25 batch! Applications are open till Nov 12.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
