University of Cambridge > Talks.cam > NLIP Seminar Series > Improving Speech Translation with Linguistically-Informed Representations

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

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

ℹī¸ Information

Improving Speech Translation with Linguistically-Informed Representations

Download to your calendar using vCal

If you have a question about this talk, please contact Guy Aglionby .

Join Zoom Meeting https://cl-cam-ac-uk.zoom.us/j/99290674837?pwd=cEYvd0pSSXgvN2VERUpmblZ3QzJiZz09

Meeting ID: 992 9067 4837 Passcode: 999939

End-to-end models for speech translation (ST) more tightly couple speech recognition (ASR) and machine translation (MT) than a traditional cascade of separate ASR and MT models, with simpler model architectures and the potential for reduced error propagation. However, several challenges still remain to make end-to-end models perform as well as cascaded models, particularly in low-resource scenarios. Further, in the move towards more task-agnostic neural architectures, inductive biases for each task have largely been removed. In this talk, I will discuss some important considerations for building speech translation models (and why we should still draw inspiration from cascades), as well as three methods to re-introduce model biases through phonologically-informed representations and the situations where they are most beneficial.

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Octagon, St. Chads, 48 Grange Road (The junction between Grange Rd. and West Rd) School of Pythagoras (Uppercroft), St. John's College Senior Parlour, Gonville & Caius College

Other talks

Morning Break Coming soon The rise of local cartography in Europe, 12th-14th century Morning Break / Group Photo Task performance predicts the substitution of feedforward by feedback drive in visual cortex Title to be confirmed
 

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