Speech recognition in a reverberant environment using matched filter array (MFA) processing and linguistic-tree maximum likelihood linear regression (LT-MLLR) adaptation
نویسندگان
چکیده
Performance of automatic speech recognition systems trained on close talking data su ers when used in a distant talking environment due to the mismatch in training and testing conditions Microphone array sound capture can reduce some mismatch by removing ambi ent noise and reverberation but o ers insu cient im provement in performance However using array sig nal capture in conjunction with Hidden Markov Model HMM adaptation on the clean speech models can re sult in improved recognition accuracy This paper de scribes an experiment in which the output of an element microphone array system using MFA process ing is used for speech recognition with LT MLLR adap tation The recognition is done in two passes In the rst pass an HMM trained on clean data is used to rec ognize the speech Using the results of this pass the HMM model is adapted to the environment using the LT MLLR algorithm This adapted model a product of MFA and LT MLLR results in improved recognition performance
منابع مشابه
Technical Report CAIP TR SPEAKER AND ENVIRONMENT ADAPTATION IN CONTINUOUS SPEECH RECOGNITION
Hidden Markov Models HMMs have been used with consider able success in continuous speech recognition It is well known that high accuracy can be obtained when the HMM system is trained and tested in a quiet environment and the speech signal is acquired from a close talking microphone However mismatches between training and testing environment severely degrade erformance Two major sources of mism...
متن کاملHMM adaptation and microphone array processing for distant speech recognition
Connected strings of seven digits from the TIDIGITS database were recorded in a reverberant office room for evaluation using microphone array processing and HMM, Hidden Markov Model, adaptation. A sixteen-channel linear microphone array records a distance speech database useful for further experimentation. The adaptation techniques of Parallel Model Combination (PMC) and Maximum Likelihood Line...
متن کاملCombining Mllr Adaptation and Feature Extraction for Robust Speech Recognition in Reverberant Environments
This paper presents an investigation on speech recognition performance in reverberant environments. Reverberant noise has been a major concern in speech recognition systems. Many speech recognition systems, even with state-of-art features, fail to respond to reverberant effects and the recognition rate deteriorates. This shows the limitations of robust feature extraction in reverberant environm...
متن کاملImprovement of MLLR Speaker Adaptation Using a Novel Method
This paper presents a technical speaker adaptation method called WMLLR, which is based on maximum likelihood linear regression (MLLR). In MLLR, a linear regression-based transform which adapted the HMM mean vectors was calculated to maximize the likelihood of adaptation data. In this paper, the prior knowledge of the initial model is adequately incorporated into the adaptation. A series of spea...
متن کاملImproving robustness of MLLR adaptation with speaker-clustered regression class trees
We introduce a strategy for modeling speaker variability in speaker adaptation based on maximum likelihood linear regression (MLLR). The approach uses a speaker clustering procedure that models speaker variability by partitioning a large corpus of speakers in the eigenspace of their MLLR transformations and learning clusterspecific regression class tree structures. We present experiments showin...
متن کامل