Model-based speech enhancement algorithms that employ trained models, such as codebooks, hidden Markov models, Gaussian mixture models, etc., containing representations of speech such as linear predictive coefficients, mel-frequency cepstrum coefficients, etc., have been found to be successful in enhancing noisy speech corrupted by nonstationary noise. However, these models are typically trained on speech data from multiple speakers under controlled acoustic conditions. In this paper, we introduce the notion of context-dependent models that are trained on speech data with one or more aspects of context, such as speaker, acoustic environment, speaking style, etc. In scenarios where the modeled and observed contexts match, context-dependent models can be expected to result in better performance, whereas context-independent models are preferred otherwise. In this paper, we present a Bayesian framework that automatically provides the benefits of both models under varying contexts. As several aspects of the context remain constant over an extended period during usage, a memory-based approach that exploits information from past data is employed. We use a codebook-based speech enhancement technique that employs trained models of speech and noise linear predictive coefficients as an example model-based approach. Using speaker, acoustic environment, and speaking style as aspects of context, we demonstrate the robustness of the proposed framework for different context scenarios, input signal-to-noise ratios, and number of contexts modeled.
Although single-microphone noise reduction methods perform well in stationary noise environments, their performance in non-stationary conditions remains unsatisfactory. Use of prior knowledge about speech and noise power spectral densities in the form of trained codebooks has been previously shown to address this limitation. While it is possible to use trained speech codebooks in a practical system, the variety of noise types encountered in practice makes the use of trained noise codebooks less practical.This letter presents a new approach that uses a generic noise codebook for speech enhancement that can be generated on-the-fly and provides good performance.
The advent of ubiquitous mobile communication has posed a lot of challenges, one of the prominent being suppression of background noise, especially in non-stationary noisy environments. In literature, several speech enhancement techniques have been proposed to tackle this problem of noise reduction. Codebook-based speech enhancement (CBSE) employing trained speech and noise codebooks, is one of the most effective noise reduction technique for handling non-stationary noise. However, the high compute intensive nature of this technique renders it inapplicable in real-time speech enhancement scenarios by introducing a significant delay in speech transmission. In this paper, this problem is addressed by providing an efficient, parallel CBSE algorithm. The proposed parallel CBSE algorithm achieves significant speedup and reduced execution time, resulting in a speech transmission delay which is well within the limits of realizing real-time speech enhancement. The proposed parallel CBSE algorithm is then used as a basis to provide a novel cloud based framework to achieve real-time speech enhancement in mobile communication as a proof-ofconcept. The proposed parallel implementation can also be used in a variety of applications which demand real-time speech enhancement such as teleconferencing systems, digital hearing aid devices and speech recognition systems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.