Hidden Markov models (HMMs) are a powerful probabilistic tool for modeling sequential data, and have been applied with success to many text-related tasks, such as part-of-speech t...
Andrew McCallum, Dayne Freitag, Fernando C. N. Per...
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 o...
Georg Heigold, Geoffrey Zweig, Xiao Li, Patrick Ng...
Multimedia presentation systems require flexible support for the modeling of multimedia content models. Many presentation systems provide the synchronized, sequential or concurren...
act— Web alerts are user-defined monitor conditions for public Internet information in which notification messages are sent to users whenever their alert conditions are met. The ...
This paper investigates the effectiveness of online temporal language model adaptation when applied to a Thai broadcast news transcription task. Our adaptation scheme works as fol...