Speech and Networking Talks on YouTube

Friday, July 19, 2013

In the last two weeks, ICSI has hosted two talks related to speech processing and one related to networking. You can check out all ICSI's videos on our YouTube account. Here are the three recent talks.

 

Zero Resources Spoken Audio Search
Xavier Anguera
Telefonica Research, Barcelona

Monday, July 15, 2013

Abstract:
In this talk I will talk about zero-resources spoken audio search, also known as Query-by-Example Spoken Term Detection. Given a corpus of audio in a single or multiple languages for which we do not have any transcripts, the objective here is to build a language independent system that allows us to locate where an audio query has been spoken in the corpus...
Read the full abstract and bio.

 

On the Importance of Internet eXchange Points for Today's Internet
Anja Feldmann
TU Berlin

Friday, July 12, 2013

Abstract:
Internet eXchange Points (IXPs) are generally considered to be the successors of the four Network Access Points that were mandated as part of the decommissioning of the NSFNET in 1994/95 to facilitate the transition to "public Internet" as we know it today. While this popular view does not tell the whole story behind the early beginnings of IXPs, what is true is that since around 1994, the number of operational IXPs worldwide has grown to more than 300 (as of May 2013) ....
Read the full abstract and bio.

 

How to Borrow a Language
Pascale Fung
Department of Electronic & Computer Engineering
The Hong Kong University of Science & Technology, Clear Water Bay, Kowloon, Hong Kong

Wednesday, July 10, 2013

Abstract:
n this talk, I will give an overview of our latest work on addressing the challenge faced by processing multilingual speech, especially those with low resources such as non-standard languages and mixed code speech. Non-standard languages such as Cantonese Chinese have little to no transcribed text for training language models. Similarly for mixed code speech, where a bilingual speaker mixes two languages in the same sentence, it is difficult to obtain enough mixed code data to train the language model. ....
Read the full abstract and bio.