Vocabulary independent discriminative term frequency estimation
نویسنده
چکیده
We introduce a discriminative approach to vocabulary independent term frequency estimation. Using two separate corpora and recognition systems, we show that our model can perform significantly better than a previously established generative model at this task.
منابع مشابه
Combining Evidence from Unconstrained Spoken Term Frequency Estimation for Improved Speech Retrieval
Title of dissertation: Combining Evidence from Unconstrained Spoken Term Frequency Estimation for Improved Speech Retrieval J. Scott Olsson, Doctor of Philosophy, 2008 Dissertation directed by: Associate Professor Douglas W. Oard College of Information Studies This dissertation considers the problem of information retrieval in speech. Today’s speech retrieval systems generally use a large vocab...
متن کاملInvestigations on discriminative training in large scale acoustic model estimation
In this paper two common discriminative training criteria, maximum mutual information (MMI) and minimum phone error (MPE), are investigated. Two main issues are addressed: sensitivity to different lattice segmentations and the contribution of the parameter estimation method. It is noted that MMI andMPE may benefit from different lattice segmentation strategies. The use of discriminative criteri...
متن کاملTerm-dependent confidence for out-of-vocabulary term detection
Within a spoken term detection (STD) system, the decision maker plays an important role in retrieving reliable detections. Most of the state-of-the-art STD systems make decisions based on a confidence measure that is term-independent, which poses a serious problem for out-of-vocabulary (OOV) term detection. In this paper, we study a term-dependent confidence measure based on confidence normalis...
متن کاملLattice segmentation and minimum Bayes risk discriminative training for large vocabulary continuous speech recognition
Lattice segmentation techniques developed for Minimum Bayes Risk decoding in large vocabulary speech recognition tasks are used to compute the statistics needed for discriminative training algorithms that estimate HMM parameters so as to reduce the overall risk over the training data. New estimation procedures are developed and evaluated for both small and large vocabulary recognition tasks, an...
متن کاملImproved discriminative training techniques for large vocabulary continuous speech recognition
This paper investigates the use of discriminative training techniques for large vocabulary speech recogntion with training datasets up to 265 hours. Techniques for improving lattice-based Maximum Mutual Information Estimation (MMIE) training are described and compared to Frame Discrimination (FD). An objective function which is an interpolation of MMIE and standard Maximum Likelihood Estimation...
متن کامل