A Hilbert-fine-structure-derived physical metric for predicting the intelligibility of noise-distorted and noise-suppressed speech

Chen, Fei; Wong, Lena L. N.; Hu, Yi

doi:10.1016/j.specom.2013.06.016

Cited by 8 publications

(7 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To overcome the limitations of the SII and STI, a number of intelligibility metrics have been proposed. Examples include the coherence SII (CSII) [15], the extended SII (ESII) [12], the quasi-stationary STI (QSTI) [16], the normalized covariance measure (NCM) [17], [18], the temporal fine-structure spectrum based index (TFSS) [19], the hearing-aid speech perception index (HASPI) [20], the Christiansen-Pedersen-Dau metric (CPD) [21], those based on the short-time objective intelligibility measure (STOI) (e.g., [22], [23]), those based on the speech-based envelope power spectrum model (sEPSM) (e.g., [24], [25], [26]), and those based on the glimpse proportion metric (GP) (e.g., [27], [28], [29]). Many of these metrics have not been extensively tested on data sets other than those used during their development.…”

Section: Introductionmentioning

confidence: 99%

An Evaluation of Intrusive Instrumental Intelligibility Metrics

Kuyk

Kleijn

Hendriks

2018

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Instrumental intelligibility metrics are commonly used as an alternative to listening tests. This paper evaluates 12 monaural intrusive intelligibility metrics: SII, HEGP, CSII, HASPI, NCM, QSTI, STOI, ESTOI, MIKNN, SIMI, SIIB, and sEPSM corr . In addition, this paper investigates the ability of intelligibility metrics to generalize to new types of distortions and analyzes why the top performing metrics have high performance. The intelligibility data were obtained from 11 listening tests described in the literature. The stimuli included Dutch, Danish, and English speech that was distorted by additive noise, reverberation, competing talkers, pre-processing enhancement, and post-processing enhancement. SIIB and HASPI had the highest performance achieving a correlation with listening test scores on average of ρ = 0.92 and ρ = 0.89, respectively. The high performance of SIIB may, in part, be the result of SIIBs developers having access to all the intelligibility data considered in the evaluation. The results show that intelligibility metrics tend to perform poorly on data sets that were not used during their development. By modifying the original implementations of SIIB and STOI, the advantage of reducing statistical dependencies between input features is demonstrated. Additionally, the paper presents a new version of SIIB called SIIB Gauss , which has similar performance to SIIB and HASPI, but takes less time to compute by two orders of magnitude.

show abstract

Section: Introductionmentioning

confidence: 99%

An Evaluation of Intrusive Instrumental Intelligibility Metrics

Kuyk

Kleijn

Hendriks

2018

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…Several studies suggested that normal-hearing listeners benefit from temporal fine structure (TFS) information in the presence of modulated maskers [18], [19]. TFS spectrum index (TFSS) [20] is a SIP algorithm that incorporates the Hilbertderived TFS information into SIP. TFSS first decomposes the input speech signals into acoustic frequency sub-bands, using multiple bandpass filters.…”

Section: Introductionmentioning

confidence: 99%

Speech Intelligibility Prediction Using Spectro-Temporal Modulation Analysis

Edraki

Chan

Jensen

et al. 2021

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

General rightsCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.-Users may download and print one copy of any publication from the public portal for the purpose of private study or research.-You may not further distribute the material or use it for any profit-making activity or commercial gain -You may freely distribute the URL identifying the publication in the public portal -A. Edraki and W.-Y. Chan are with the

show abstract

“…Several early studies point out the unimportance [1] and importance [2][3][4] of spectral phase information from a perceptual viewpoint. Several more recent studies reported positive impact of spectral phase in different speech processing applications including speech enhancement [5][6][7][8], speech intelligibility prediction [9,10] and ASR [11] (see [12,13] for an overview). Conventional automatic speech recognition (ASR) systems often rely solely on the magnitude spectrum and are built upon short-time amplitude-derived features [14].…”

Section: Introductionmentioning

confidence: 99%

Phase-Aware Signal Processing for Automatic Speech Recognition

et al. 2016

View full text Add to dashboard Cite

Conventional automatic speech recognition (ASR) often neglects the spectral phase information in its front-end and feature extraction stages. The aim of this paper is to show the impact that enhancement of the noisy spectral phase has on ASR accuracy when dealing with speech signals corrupted with additive noise. Apart from proof-of-concept experiments using clean spectral phase, we also present a phase enhancement method as a phase-aware front-end and modified group delay as a phaseaware feature extractor, and the combination thereof. In experiments, we demonstrate the improved performance for each individual component and their combination, compared to the conventional phase-unaware Mel Frequency Cepstral Coefficients (MFCCs)-based ASR. We observe that the estimated phase information used in the front-end or feature extraction component improves the ASR word accuracy rate (WAR) by 20.98 % absolute for noise corrupted speech (averaged over SNRs ranging from 0 to 20 dB).

show abstract

A Hilbert-fine-structure-derived physical metric for predicting the intelligibility of noise-distorted and noise-suppressed speech

Cited by 8 publications

References 37 publications

An Evaluation of Intrusive Instrumental Intelligibility Metrics

An Evaluation of Intrusive Instrumental Intelligibility Metrics

Speech Intelligibility Prediction Using Spectro-Temporal Modulation Analysis

Phase-Aware Signal Processing for Automatic Speech Recognition

Contact Info

Product

Resources

About