Confidence measure (CM) estimation for large vocabulary speaker-independent continuous speech recognition system
نویسندگان
چکیده
In this paper we report a study for confidence measure estimation in a large vocabulary speaker-independent continuous speech recognition system. A hybrid confidence measure estimation algorithm was developed. The final confidence measure consists of a number of confidence parameters which are generated from the different processing levels of the recognition system. A Parameter Reliability Analysis (PRA) algorithm was proposed to combine the confidence parameters to form the final confidence measure. The approach was applied to a large vocabulary speaker-independent continuous speech recognition system and obtained superior performance.
منابع مشابه
Speaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملVocabulary-independent word confidence measure using subword features
This paper discusses how to compute word-level confidence measures based on sub-word features for large-vocabulary speaker-independent speech recognition. The performance of confidence measure using features at word, phone and senone level is experimentally studied. A framework of transformation function based system using sub-word features is proposed for high performance confidence estimation...
متن کاملSpeaker-independent upfront dialect adaptation in a large vocabulary continuous speech recognizer
Large vocabulary continuous speech recognition systems show a signi cant decrease in performance if a users pronunciation di ers largely from those observed during system training. This can be considered as the main reason why most commercially available systems recommend| if not enforce | the individual end user to read an enrollment script for the speaker dependent reestimation of acoustic mo...
متن کاملGeneralized mel frequency cepstral coefficients for large-vocabulary speaker-independent continuous-speech recognition
The focus of a continuous speech recognition process is to match an input signal with a set of words or sentences according to some optimality criteria. The first step of this process is parameterization, whose major task is data reduction by converting the input signal into parameters while preserving virtually all of the speech signal information dealing with the text message. This contributi...
متن کامل