Using X-grams for Speech-t

Using x-grams for speech-to-speech translation

Using x-gram for efficient speech recognition

X-grams are a generalization of the n-grams, where the number of previous conditioning words is different for each case and decided from the training data. X-grams reduce perplexity with respect to trigrams and need less number of parameters. In this paper, the representation of the x-grams using finite state automata is considered. This representation leads to a new model, the non-deterministi...

Using X-grams for Speech-to

In this paper, a statistical speech-to-speech translation system, developed at TALP during the last months, is presented. By adapting well-known speech recognition techniques to the specific translation setting, the system is able to integrate speech signal into a finite state transducer that translates statistically domain-constrained Spanish sentences into English ones.

Interpolated Dirichlet Class Language Model for Speech Recognition Incorporating Long-distance N-grams

We propose a language modeling (LM) approach incorporating interpolated distanced n-grams in a Dirichlet class language model (DCLM) (Chien and Chueh, 2011) for speech recognition. The DCLM relaxes the bag-of-words assumption and documents topic extraction of latent Dirichlet allocation (LDA). The latent variable of DCLM reflects the class information of an n-gram event rather than the topic in...

Inferring Selectional Preferences from Part-Of-Speech N-grams

We present the PONG method to compute selectional preferences using part-of-speech (POS) N-grams. From a corpus labeled with grammatical dependencies, PONG learns the distribution of word relations for each POS N-gram. From the much larger but unlabeled Google N-grams corpus, PONG learns the distribution of POS N-grams for a given pair of words. We derive the probability that one word has a giv...