Journal Article10.1109/TASL.2007.911054
Evaluation of Objective Quality Measures for Speech Enhancement
Yi Hu,Philipos C. Loizou +1 more
1.9K
TL;DR: The evaluation of correlations of several objective measures with these three subjective rating scales is reported on and several new composite objective measures are also proposed by combining the individual objective measures using nonparametric and parametric regression analysis techniques.
read more
Abstract: In this paper, we evaluate the performance of several objective measures in terms of predicting the quality of noisy speech enhanced by noise suppression algorithms. The objective measures considered a wide range of distortions introduced by four types of real-world noise at two signal-to-noise ratio levels by four classes of speech enhancement algorithms: spectral subtractive, subspace, statistical-model based, and Wiener algorithms. The subjective quality ratings were obtained using the ITU-T P.835 methodology designed to evaluate the quality of enhanced speech along three dimensions: signal distortion, noise distortion, and overall quality. This paper reports on the evaluation of correlations of several objective measures with these three subjective rating scales. Several new composite objective measures are also proposed by combining the individual objective measures using nonparametric and parametric regression analysis techniques.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Noise-Robust Voice Activity Detector Based on Hidden Semi-Markov Models
Xianglong Liu,Yuan Liang,Yihua Lou,He Li,Baosong Shan +4 more
- 23 Aug 2010
TL;DR: A noise-robust and real-time voice activity detector (VAD) using the hidden semi-Markov model (HSMM) to explicitly model state durations is proposed and performs more robustly and accurately than the standard ITU-T G.729B VAD and AMR2.
9
Analysis of trade-offs between magnitude and phase estimation in loss functions for speech denoising and dereverberation
TL;DR: In this paper , a trade-off between phase recovery and magnitude estimation was analyzed for different speech enhancement tasks, and it was verified that a reasonable tradeoff between magnitude estimation and phase recovery can improve speech quality and intelligibility.
9
Deep Neural Network based Supervised Speech Enhancement in Speech-Babble Noise
Nasir Saleem,Muhammad Irfan,Xuhui Chen,Muhammad Ali +3 more
- 06 Jun 2018
TL;DR: A supervised learning approach to enhance a speech degraded by speech-babble noise, which is most challenging type of noise in speech enhancement systems, and results revealed that the DNN-LW approach performs significantly better against baseline speech enhancement methods.
9
Speech enhancement in spectral envelope and details subspaces
TL;DR: This study addresses the overlapped spectral bases between speech and noise components in spectral dictionary space through a combination strategy of spectral modulation decoupling and low-rank and sparsity oriented decomposition in spectral envelop subspace.
9
Patent
Method, computer, computer program and computer program product for speech quality estimation
Volodya Grancharov,Mats Folkesson +1 more
- 26 Jul 2010
TL;DR: In this article, the authors proposed a method, computer, computer program and computer program product for speech quality estimation, which comprises the steps of: determining a coding distortion parameter (QCOD), a bandwidth related distortion (BW) and a presentation level distortion (PL) of a speech signal; extracting a first coefficient (ω 1 ) and a second coefficient(ω 2 ), the first coefficient and the second coefficient being dependent on the coding distortion parameters; and calculating a signal quality measure (Q), where the signal quality measures is Q COD + ω 1 Bw +
9
References
Multivariate Adaptive Regression Splines
TL;DR: In this article, a new method is presented for flexible regression modeling of high dimensional data, which takes the form of an expansion in product spline basis functions, where the number of basis functions as well as the parameters associated with each one (product degree and knot locations) are automatically determined by the data.
Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs
Antony William Rix,John G. Beerends,Michael Peter Hollier,Andries Pieter Hekstra +3 more
- 07 May 2001
TL;DR: A new model has been developed for use across a wider range of network conditions, including analogue connections, codecs, packet loss and variable delay, known as perceptual evaluation of speech quality (PESQ).
2.8K
•Book
Speech Enhancement: Theory and Practice
Philipos C. Loizou
- 07 Jun 2007
TL;DR: Clear and concise, this book explores how human listeners compensate for acoustic noise in noisy environments and suggests steps that can be taken to realize the full potential of these algorithms under realistic conditions.
2.5K
Evaluation of Objective Quality Measures for Speech Enhancement
Yi Hu,Philipos C. Loizou +1 more
TL;DR: The evaluation of correlations of several objective measures with these three subjective rating scales is reported on and several new composite objective measures are also proposed by combining the individual objective measures using nonparametric and parametric regression analysis techniques.
1.9K