A confidence-guided dynamic pruning approach - utilization of confidence measurement in speech recognition
نویسندگان
چکیده
Improved efficiency of pruning accelerates the search process and leads to a more time efficient speech recognition system. The goal of this work was to develop a new pruning technique which optimizes the well known probability-based pruning (beam width) by utilization of confidence measurement. We use normalized hypotheses scores to guide the beam width of the pruning process dynamically frame per frame during the whole utterance. Compared with classical pruning techniques like fixed beam pruning and histogram rank pruning we achieved significantly better results concerning the time consumption of the recognizer. The speed of the recognition process could be accelerated up to 14 times with a slight degradation in recognition accuracy.
منابع مشابه
Confidence measurement techniques in automatic speech recognition and dialog management
Reliable confidence measures are essential to the basis of decisionmaking for enriching human-machine speech interaction with necessary intelligence in ergonomic dialog management. In addition to a survey of the state of the art in confidence measurement, this work also provides classification of methods derivated from several points of view and describes possible fields of application. The the...
متن کاملDynamic tuning of language model score in speech recognition using a confidence measure
Speech recognition errors limit the capability of language models to predict subsequent words correctly. An effective way to enhance the functions of the language model is by using confidence measures. Most of current efforts for developing confidence measures for speech recognition focus on applying these measures to the final recognition result. However, using these measures early in the sear...
متن کاملرویکردی به ارزیابی سرمایه اجتماعی در اقتصاد ایران
Economic literature in 1990s notifies that the larger a nation’s social capital is, the more fortunate and wealthier the nation would be. Social capital or social part of production function is a nation’s historical heritage that aids the civil society in solving its problems through confidence factor. Civil society institutions encourage the option of cooperation strategy by means of informati...
متن کاملUnsupervised speaker adaptation using high confidence portion recognition results by multiple recognition systems
This paper describes an accurate unsupervised speaker adaptation method for lecture speech recognition using multiple LVCSRs. In an unsupervised speaker adaptation framework, the improvement of recognition performance by adapting acoustic models greatly depends on the accuracy of labels such as phonemes and syllables. Therefore, extraction of the adaptation data guided by the confidence measure...
متن کاملReducing computation on parallel decoding using frame-wise confidence scores
Parallel decoding based on multiple models has been studied to cover various conditions and speakers at a time on a speech recognition system. However, running many recognizers in parallel applying all models causes the total computational cost to grow in proportion to the number of models. In this paper, an efficient way of finding and pruning unpromising decoding processes during search is pr...
متن کامل