This paper describes a technique for reduction of non-stationary noise in electronic voice communication systems. Removal of noise is needed in many such systems, particularly those deployed in harsh mobile or otherwise dynamic acoustic environments. The proposed method employs state-based statistical models of both speech and noise, and is thus capable of tracking variations in noise during su...

A speech enhancement algorithm that is based on a connected-word hidden Markov model (HMM) is developed. Speech is assumed to be highly degraded by statistically independent additive noise. The minimum mean square error estimator is derived for a connected-word HMM. Further, we derive an estimator based on a connected-word HMM with explicit state duration. Listening experiments performed with d...

A New system for speech enhancement, that uses hidden markov models (HMM) with noise-robust features, is developed. This system alleviates the error in decoding the noisy speech, that was observed in the conventional modelbased enhancement system [2] . This decoding error results in a degradation in the performance of the conventional system from its theoretical upper limits. A comparative test...

Abstract In this paper, we propose a supervised single-channel speech enhancement method that combines Kullback-Leibler (KL) divergence-based non-negative matrix factorization (NMF) and hidden Markov model (NMF-HMM). With the integration of HMM, temporal dynamics information signals can be taken into account. This includes training stage an stage. stage, sum Poisson distribution, leading to KL ...

In this paper we propose a novel iterative speech feature enhancement and recognition architecture for noisy speech recognition. It consists of model-based feature enhancement employing Switching Linear Dynamical Models (SLDM), a hidden Markov Model (HMM) decoder and a state mapper, which maps HMM to SLDM states. To consistently adhere to a Bayesian paradigm, posteriors are exchanged between th...

The use of HMM (Hidden Markov Models) for speech recognition has been successful for various applications in the past decades. However, the use of continuous HMM (CHMM) for melody recognition via acoustic input (MRAI for short), or the so-called query by singing/humming, has seldom been reported, partly due to the difference in acoustic characteristics between speech and singing/humming inputs....

In this paper we propose to combine audio-visual speech recognition with inventory-based speech synthesis for speech enhancement. Unlike traditional filtering-based speech enhancement, inventory-based speech synthesis avoids the usual trade-off between noise reduction and consequential speech distortion. For this purpose, the processed speech signal is composed from a given speech inventory whi...

This study presents a new approach for robust speech activity detection (SAD). Our framework is based on HMM recognition of speech versus silence. We model speech as one of fourteen large phone classes whereas silence is represented as a separate model. Individual test utterances are concatenated to simulate read continuous speech for testing. The HMM-based algorithm is compared to both an ener...