Discriminatively derived HMM-based announcement modeling approach for noise control avoiding the problem of false alarms
نویسندگان
چکیده
Earlier we proposed modeling echo residuals by using multiple echo models built from a set of speci c announcement. Experienced callers may interrupt the prompt by speaking the keywords over the prompt. This leads to incomplete prompt echoes that was not properly modeled by multiple echo models. In this study, we investigate further improvements by building an echo model of each word in the entire announcement, then linking each model in sequence to track the exact echo that precedes valid speech (movie title). The experimental results show that by modeling exactly, one can get better recognition accuracy and less false triggering, with a possible increase in computational complexity.
منابع مشابه
HMM-based echo and announcement modeling approaches for noise suppression avoiding the problem of false triggers
In the past, we proposed an HMM-based residual echo modeling technique that proved to be e ective in eliminating false triggering and enhanced the recognition of valid keyword speech. The narrow training strategy based on single recorded prompt made the echo model a better discriminator, though it has the possible drawback of requiring retraining if the prompt changes. To overcome this intrinsi...
متن کاملTransition Potential Modeling of Land-Cover based on Similarity Weighted Instance-based Learning Procedure and Its Implication in the REDD Project Design Document
Reducing Emissions from Deforestation and Forest Degradation (REDD) is a climate change mitigation strategy employed to reduce the intensity of deforestation and GHGS emissions. In recent decades, drastic land use changes in Mazandaran province caused a substantial reduction in the amount of Hyrcanian forests. The present research based on objectives of REDD projects paid to identify of fore...
متن کاملSpeech enhancement based on hidden Markov model using sparse code shrinkage
This paper presents a new hidden Markov model-based (HMM-based) speech enhancement framework based on the independent component analysis (ICA). We propose analytical procedures for training clean speech and noise models by the Baum re-estimation algorithm and present a Maximum a posterior (MAP) estimator based on Laplace-Gaussian (for clean speech and noise respectively) combination in the HMM ...
متن کاملAn artificial Neural Network approach to monitor and diagnose multi-attribute quality control processes
One of the existing problems of multi-attribute process monitoring is the occurrence of high number of false alarms (Type I error). Another problem is an increase in the probability of not detecting defects when the process is monitored by a set of independent uni-attribute control charts. In this paper, we address both of these problems and consider monitoring correlated multi-attributes proce...
متن کاملOptimal design of a vibration absorber for tremor control of arm in Parkinson's disease
Because the underlying physiology of pathological tremor in a Parkinson's patient is not well understood, the existing physical and drug therapies have not been successful in tremor treatment. Different mathematical modeling of such vibration has been introduced to investigate the problem and reduce the existing vibration. Most of the models have represented the induced vibration as a sinusoida...
متن کامل