Learn More
A recent trial of natural language call steering on live UK calls to the operator is described along with its results. The characteristics of the problem are described along with the acoustic, language, semantic and dialogue modelling approaches employed. Natural language call steering is found to be viable, with recognition and semantic accuracy the(More)
This paper presents a new perspective to the language modeling problem by moving the word representations and modeling into the continuous space. In a previous work we introduced Gaussian-Mixture Language Model (GMLM) and presented some initial experiments. Here, we propose Tied-Mixture Language Model (TMLM), which does not have the model parameter(More)
This paper presents an enhanced stochastic mapping technique in the discriminative feature (fMPE) space that exploits stereo data for noise robust LVCSR. Both MMSE and MAP estimates of the mapping are given and the performance of the two is investigated. Due to the iterative nature of the MAP estimate, we show that combining MMSE and MAP estimates is(More)
This paper focuses on comparison of two continuous space language modeling techniques, namely Tied–Mixture Language modeling (TMLM) and Neural Network Based Language Modeling (NNLM). Additionally, we report on using alternative feature representations for words and histories used in TMLM. Besides bigram co–occurrence based features we consider using NNLM(More)
Arabic has a large number of affixes that can modify a stem to form words. In automatic speech recognition (ASR) this leads to a high out-of-vocabulary (OOV) rate for typical lexicon size, and hence a potential increase in WER. This is even more pronounced for dialects of Arabic where additional affixes are often introduced and the available data is(More)
The first part of this paper describes the BBN system that participated in the 2004 broadcast news (BN) evaluation for Arabic. The complete system description is given together with experimental results on the 2004 development, and evaluation sets. Previous Arabic speech recognition at BBN used grapheme models due to the lack of short vowel information in(More)