Confidence based lattice segmentation and minimum Bayes-risk decoding
نویسندگان
چکیده
Minimum Bayes Risk (MBR) speech recognizers have been shown to yield improvements over the conventional maximum a-posteriori probability (MAP) decoders in the context of Nbest list rescoring and A search over recognition lattices. Segmental MBR (SMBR) procedures have been developed to simplify implementation of MBR recognizers, by segmenting the N-best list or lattice, to reduce the size of the search space over which MBR recognition is carried out. In this paper we describe lattice cutting as a method to segment recognition word lattices into regions of low confidence and high confidence. We present two SMBR decoding procedures that can be applied on low confidence segment sets. Results obtained on the Switchboard conversational telephone speech corpus show modest but significant improvements relative to MAP decoders.
منابع مشابه
Risk based lattice cutting for segmental minimum Bayes-risk decoding
Minimum Bayes Risk (MBR) decoders improve upon MAP decoders by directly optimizing loss function of interest: Word Error Rate MBR decoding is expensive when the search spaces are large Segmental MBR (SMBR) decoding breaks the single utterance-level MBR decoder into a sequence of simpler search problems. – To do this, the N-best lists or lattices need to be segmented We present: A new lattice se...
متن کاملRisk Based Lattice Cut Segmental Minimum Bayes-r
Minimum Bayes-Risk (MBR) speech recognizers have been shown to give improvements over the conventional maximum a-posteriori probability (MAP) decoders through N-best list rescoring and A search over word lattices. Segmental MBR (SMBR) decoders simplify the implementation of MBR recognizers by segmenting the N-best lists or lattices over which the recognition is performed. We present a lattice c...
متن کاملMinimum Bayes Risk Estimation and Decoding in Large Vocabulary Continuous Speech Recognition
Minimum risk estimation and decoding strategies based on lattice segmentation techniques can be used to refine large vocabulary continuous speech recognition systems through the estimation of the parameters of the underlying hidden Mark models and through the identification of smaller recognition tasks which provides the opportunity to incorporate novel modeling and decoding procedures in LVCSR...
متن کاملCorrections to "Segmental minimum Bayes-risk decoding for automatic speech recognition"
In our recently published paper [1], we presented a risk-based lattice cutting procedure to segment ASR word lattices into smaller sub-lattices as a means to to improve the efficiency of Minimum Bayes-Risk (MBR) rescoring. In the experiments reported [1], some of the hypotheses in the original lattices were inadvertently discarded during segmentation, and this affected MBR performance adversely...
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 کامل