Sciweavers

ICASSP
2009
IEEE

A flat direct model for speech recognition

13 years 10 months ago
A flat direct model for speech recognition
We introduce a direct model for speech recognition that assumes an unstructured, i.e., flat text output. The flat model allows us to model arbitrary attributes and dependences of the output. This is different from the HMMs typically used for speech recognition. This conventional modeling approach is based on sequential data and makes rigid assumptions on the dependences. HMMs have proven to be convenient and appropriate for large vocabulary continuous speech recognition. Our task under consideration, however, is the Windows Live Search for Mobile (WLS4M) task [1]. This is a cellphone application that allows users to interact with web-based information portals. In particular, the set of valid outputs can be considered discrete and finite (although probably large, i.e., unseen events are an issue). Hence, a flat direct model lends itself to this task, making the adding of different knowledge sources and dependences straightforward and cheap. Using e.g. HMM posterior, m-gram, and spo...
Georg Heigold, Geoffrey Zweig, Xiao Li, Patrick Ng
Added 21 May 2010
Updated 21 May 2010
Type Conference
Year 2009
Where ICASSP
Authors Georg Heigold, Geoffrey Zweig, Xiao Li, Patrick Nguyen
Comments (0)