Speech intelligibility prediction using a Neurogram Similarity Index Measure

Hines, Andrew; Harte, Naomi

doi:10.1016/j.specom.2011.09.004

Cited by 70 publications

(41 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ViSQOL was inspired by prior work on speech intelligibility by two of the authors [32,33]. This work used a model of the auditory periphery [34] to produce auditory nerve discharge outputs by computationally simulating the middle and inner ear.…”

Section: Measuring Speech Quality Through Spectrogram Similaritymentioning

confidence: 99%

“…Each reference patch is aligned with the corresponding area from the test spectrogram. The Neurogram Similarity Index Measure (NSIM) [33] is used to measure the similarity between the reference patch and a test spectrogram patch frame by frame, thus identifying the maximum similarity point for each patch. This is shown in the bottom pane of Figure 5 where each line graphs the NSIM similarity score over time for each patch in the reference signal compared with the example signal.…”

Section: Time Alignmentmentioning

confidence: 99%

“…Prior work [32,33] demonstrated that the structural similarity index (SSIM) [35] could be used to discriminate between reference and degraded images of speech to predict intelligibility. SSIM was developed to evaluate JPEG compression techniques by assessing image similarity relative to a reference uncompressed image.…”

Section: Similarity Comparisonmentioning

confidence: 99%

See 2 more Smart Citations

ViSQOL: an objective speech quality model

Hines

Skoglund

Kokaram

et al. 2015

J AUDIO SPEECH MUSIC PROC.

Self Cite

View full text Add to dashboard Cite

This paper presents an objective speech quality model, ViSQOL, the Virtual Speech Quality Objective Listener. It is a signal-based, full-reference, intrusive metric that models human speech quality perception using a spectro-temporal measure of similarity between a reference and a test speech signal. The metric has been particularly designed to be robust for quality issues associated with Voice over IP (VoIP) transmission. This paper describes the algorithm and compares the quality predictions with the ITU-T standard metrics PESQ and POLQA for common problems in VoIP: clock drift, associated time warping, and playout delays. The results indicate that ViSQOL and POLQA significantly outperform PESQ, with ViSQOL competing well with POLQA. An extensive benchmarking against PESQ, POLQA, and simpler distance metrics using three speech corpora (NOIZEUS and E4 and the ITU-T P.Sup. 23 database) is also presented. These experiments benchmark the performance for a wide range of quality impairments, including VoIP degradations, a variety of background noise types, speech enhancement methods, and SNR levels. The results and subsequent analysis show that both ViSQOL and POLQA have some performance weaknesses and under-predict perceived quality in certain VoIP conditions. Both have a wider application and robustness to conditions than PESQ or more trivial distance metrics. ViSQOL is shown to offer a useful alternative to POLQA in predicting speech quality in VoIP scenarios.

show abstract

Section: Measuring Speech Quality Through Spectrogram Similaritymentioning

confidence: 99%

Section: Time Alignmentmentioning

confidence: 99%

See 1 more Smart Citation

ViSQOL: an objective speech quality model

Hines

Skoglund

Kokaram

et al. 2015

J AUDIO SPEECH MUSIC PROC.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Each reference patch is aligned with the corresponding area from the test spectrogram. The Neurogram Similarity Index Measure (NSIM) [11] is used to align and measure the similarity between the reference and a test spectrogram patches, as in Figure 1. The NSIM score per patch is averaged over the patches to yield the similarity metric for the test signal.…”

Section: Visqol Modelmentioning

confidence: 99%

Detailed comparative analysis of PESQ and VISQOL behaviour in the context of playout delay adjustments introduced by VOIP jitter buffer algorithms

Hines

Počta

Melvin

2013

2013 Fifth International Workshop on Quality of Multimedia Experience (QoMEX)

Self Cite

View full text Add to dashboard Cite

This paper undertakes a detailed comparative analysis of both PESQ and VISQOL model behaviour, when tested against speech samples modified through playout delay adjustments. The adjustments are typical (in extent and magnitude) to those introduced by VoIP jitter buffer algorithms. Furthermore, the analysis examines the impact of adjustment location as well as speaker factors on MOS scores predicted by both models and seeks to determine if both models are able to correctly predict the impact on quality perceived by the end user from earlier subjective tests. The earlier results showed speaker voice preference and potentially wideband experience dominating subjective tests more than playout delay adjustment duration or location. By design, PESQ and VISQOL do not qualify speaker voice difference reducing their correlation with the subjective tests. In addition, it was found that PESQ scores are impacted by playout delay adjustments and thus the impact of playout delay adjustments on a quality perceived by the end user is not well modelled. On the other hand, VISQOL model is better in predicting an impact of playout delay adjustments on a quality perceived by the user but there are still some discrepancies in the predicted scores. The reasons for those discrepancies are particularly analysed and discussed.

show abstract

“…This work considers four metrics from this perspective. A Structural Similarity Metric (SSIM) originating from image compression analysis has been successfully applied recently to time-frequency representations of biological neurogram signals [7] and speech signals [8], prompting the current study into its use for aeroacoustics. For images, the optimal compression stores an acceptable representation of the image as compactly as possible, ignoring extraneous detail and retaining only the information most important for human interpretation (i.e.…”

Section: Introductionmentioning

confidence: 99%

Comparison of metrics for the evaluation of similarity in acoustic pressure signals

Breakey

Meskell

2013

Journal of Sound and Vibration

View full text Add to dashboard Cite

Determining if aeroacoustic sound predictions are accurate is difficult because the question of how to define 'accurate' remains open. This communication evaluates four metrics for comparing time-domain pressure signals, each implying its own definition of 'accurate.' An adaptation of a Structural Similarity Metric (originating from image processing literature) to time-frequency representations of acoustic signals is shown to outperform typical metrics such as relative energy and mean square error.

show abstract

Speech intelligibility prediction using a Neurogram Similarity Index Measure

Cited by 70 publications

References 31 publications

ViSQOL: an objective speech quality model

ViSQOL: an objective speech quality model

Detailed comparative analysis of PESQ and VISQOL behaviour in the context of playout delay adjustments introduced by VOIP jitter buffer algorithms

Comparison of metrics for the evaluation of similarity in acoustic pressure signals

Contact Info

Product

Resources

About