On phase importance in parameter estimation in single-channel speech enhancement

Mowlaee, Pejman; Saeidi, Rahim

doi:10.1109/icassp.2013.6639113

Cited by 23 publications

(11 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dependency of the phase-based features on the starting sample window and difficulties of phase unwrapping are two challenges in combining phase information with MFCCs. Different phase unwrapping methods have been studied and group delay-based phase information has been proposed to address these challenges and to make the phase information less sensitive to the phase warping issue [31][32][33][34][35]. The fast changes of phase spectrum according to the position of a window could be more critical for applying multiple parallel window functions in multitapering methods.…”

Section: Multitaper Phase Information Extractionmentioning

confidence: 99%

Multitaper MFCC and normalized multitaper phase-based features for speaker verification

Mansouri

Castillo-Guerra

2019

SN Appl. Sci.

View full text Add to dashboard Cite

One trend of current research activity in speaker verification systems focuses on features that capture complementary information to the Mel-frequency cepstral coefficients (MFCCs). In conventional speaker verification methods, MFCCs are usually computed from a single-tapered DFT spectrum. These methods use the power of the Fourier transform of the time-domain speech frames and ignore the phase component due to its large amount of uncertainty. The multitaper phase information has been also ignored when the multitaper MFCC method applies. We propose a phase information extraction method that normalizes the change variation in the multitaper phase. The goal of this work is to incorporate phase information using low-variance multitaper spectrum estimation method instead of conventional single-taper window and normalizes the change variation in multitaper phase according to the frame position of the input speech to reduce the uncertainty of multitaper phase information in both the state-of-the-art Gaussian mixture model-universal background model (GMM-UBM) baseline and the i-vector speaker verification system. The experiments are conducted on the TIMIT database for both the clean and noisy conditions (SNR = 10 dB). The multitaper inverted-MFCC is also added to the overall system to produce diversity with respect to the fused subsystem. The results show relative improvement of 34% and 25% in terms of equal error rate (EER) over the MFCC baseline in clean and noisy conditions for GMM-UBM system, respectively. The relative improvement in terms of EER with i-vector back-end are about 36% and 16% in clean and noisy conditions as well.

show abstract

Section: Multitaper Phase Information Extractionmentioning

confidence: 99%

Multitaper MFCC and normalized multitaper phase-based features for speaker verification

Mansouri

Castillo-Guerra

2019

SN Appl. Sci.

View full text Add to dashboard Cite

show abstract

“…The initial phase can be approximated by noisy phase. In the context of signal separation, a general version of MMSE (minimum mean square error) estimate that includes an estimated phase based on an estimated magnitude was proposed by Moulaee et al [20,21].…”

Section: Introductionmentioning

confidence: 99%

Phase randomization - A new paradigm for single-channel signal enhancement

Sugiyama

Miyahara

2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

This paper proposes a new paradigm with phase randomization for single-channel signal enhancement. In contrast to literatures which pursue better target signal quality, the new method tries to minimize artifacts in the residual noise. Applications of signal enhancement are revisited to highlight today's examples where environmental signal is often considered as a part of target and SNR may take a negative value. A signal example demonstrates that conventional signal enhancement with magnitude-only modification is insufficient from both objective and subjective points of view. A new framework with phase randomization as well as a specific algorithm is developed. Enhanced signals show that phase randomization is an integral component for sufficient enhancement. A subjective evaluation result demonstrates that the new paradigm with phase randomization is superior to the magnitude-only enhancement with statistically significant differences.

show abstract

“…In model-based approaches, SCSS relies entirely on prior knowledge about the speakers (sources) in a given mixture. Sources-specific models are exploited to learn the constraints on parameters that characterise each speaker [3,4]. Model-based approaches are well-known as learning methods that are mainly based on statistical models, such as vector quantisation, Gaussian mixture models, and hidden Markov models.…”

Section: Introductionmentioning

confidence: 99%

Phase‐aware subspace decomposition for single channel speech separation

Wiem

Anouar

Bouzid

2020

IET signal process.

View full text Add to dashboard Cite

Single channel speech separation (SCSS) is often required as post-processing in several applications that facilitate automatic human-to-human or human-to-machine communication in challenging acoustic environments such as voice command for smart homes or robotics. The proposed SCSS system, that the authors call phase-aware subspace decomposition (PASD), relies on subspace decomposition for speech separation followed by a phase-aware mask for final subspace recovery. In fact, the proposed approach decomposes the mixture into a sparse and low-rank subspace in the frequency domain by rank minimising that relies on iterative decomposition using adaptive thresholding in each iteration to achieve soft estimation and considers phase-information for reconstruction. Separation results are reported in terms of both intrusive and non-intrusive metrics using realistic recordings corrupted with real-life noises. As speech separation systems are expected to have maximal interference rejection without speech distortion, we also evaluate the proposed system by recognising speech from a target speaker in the presence of either concurrent speech or noise. Recognition results show that separated signals are of high intelligibility so that they can be exploited by other automatic applications. The extensive evaluation under different test scenarios proves that PASD consistently improves the quality of the separated signals, compared to other benchmark approaches.

show abstract

On phase importance in parameter estimation in single-channel speech enhancement

Cited by 23 publications

References 24 publications

Multitaper MFCC and normalized multitaper phase-based features for speaker verification

Multitaper MFCC and normalized multitaper phase-based features for speaker verification

Phase randomization - A new paradigm for single-channel signal enhancement

Phase‐aware subspace decomposition for single channel speech separation

Contact Info

Product

Resources

About