In recent work, we proposed an alternative to parallel text as translation model (TM) training data: audio recordings of parallel speech (pSp), as it occurs in any communication s...
Language models for speech recognition tend to be brittle across domains, since their performance is vulnerable to changes in the genre or topic of the text on which they are trai...
Performance of n-gram language models depends to a large extent on the amount of training text material available for building the models and the degree to which this text matches...
We explore morphology-based and sub-word language modeling approaches proposed for morphologically rich languages, and evaluate and contrast them for Turkish broadcast news transc...
This paper investigates unsupervised vocabulary and language model self-adaptation (VLA) from just one speech file using the web as a knowledge source and without prior knowledge...