University of Cambridge > Talks.cam > Inference Group > Open Vocabulary Confusion Networks for Speech Recognition

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Open Vocabulary Confusion Networks for Speech Recognition

Download to your calendar using vCal

If you have a question about this talk, please contact Christian Steinruecken .

A limitation of most current speech recognizers is that they only recognize words from a fixed vocabulary. If the user utters a novel word, the recognizer can only indicate it doesn’t know, or choose the “least-worst” word in its vocabulary. In this paper, I explore a technique for addressing this deficiency using automatically derived units made up of letters and phones. I show how these units can be merged to form likely new words. I further give an algorithm for doing this merger while maintaining a word lattice structure. This allows construction of a word confusion network containing both in- and out-of-vocabulary (OOV) words. Experiments show these open vocabulary confusion networks provide improved word recognition rates of up to 24% relative.

Further details can be found in the paper or in chapter 6 of my thesis

This talk is part of the Inference Group series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Heritage in the making: dealing with legacies of Fascist Italy and Nazi Germany Networking with IndieBio: The world's largest seed biotech accelerator Wolfson Hall, Churchill Co

Other talks

What Can a Spectrum Learn? AI Perspectives on the Kohn Laplacian of Sphere Quotients The Magic of Magnetism Bigger Picture Talk: Developing future marine engines running on ammonia and other green fuels Tea and Coffee Break Coming soon Welfare Reform and the Imperative of Cooperation
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity