Effects of noise suppression on intelligibility. II: An attempt to validate physical metrics

Hilkhuysen, Gaston; Gaubitch, Nikolay D.; Brookes, Mike; Huckvale, Mark

doi:10.1121/1.4837238

Cited by 7 publications

(3 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However we would note that in the prediction of a probability, a binomial distribution of scores would be expected, with error better measured in terms of log odds. A proposed method for this is described in [16].…”

Section: Discussionmentioning

confidence: 99%

ELO-SPHERES intelligibility prediction model for the Clarity Prediction Challenge 2022

Huckvale¹,

Hilkhuysen²

2022

Interspeech 2022

View full text Add to dashboard Cite

This paper describes and evaluates the ELO-SPHERES project sentence intelligibility model for the Clarity Prediction Challenge 2022. The aim of the model is to make predictions of the intelligibility of enhanced speech to hearing impaired listeners. Input to the model are binaural processed audio of short sentences generated in a simulated noisy and reverberant environment together with the original source audio. Output of the model is a prediction of the intelligibility of each sentence in terms of percentage words correct for a known hearingimpaired listener characterized by a pure-tone audiogram. Models are evaluated in terms of the root mean squared error of prediction. We approached this problem in three stages: (i) evaluation of the influences of the scene metadata on scores, (ii) construction of classifiers for estimation of scene metadata from audio, and (iii) training a non-linear regression model on the challenge data and evaluation using 5-fold cross validation. On the test data, a baseline system using only the standard short-time objective intelligibility metric on the better ear achieved a RMS prediction error of 27%, while our model that also took into account given and estimated scene data achieved an RMS error of 22%.

show abstract

Section: Discussionmentioning

confidence: 99%

ELO-SPHERES intelligibility prediction model for the Clarity Prediction Challenge 2022

Huckvale¹,

Hilkhuysen²

2022

Interspeech 2022

View full text Add to dashboard Cite

show abstract

“…A number of more recent metrics are based on the correlation of the spectral amplitude modulation of the clean and degraded speech signals in each frequency band (see [18]). The most successful of these is STOI [19] which has been found to correlate well with the subjective intelligibility of both unenhanced and enhanced noisy speech signals [20,21,22]. Accordingly, in this paper, we advocate an oracle mask that optimises STOI.…”

Section: Objective Intelligibility Measurementioning

confidence: 92%

SOBM - a binary mask for noisy speech that optimises an objective intelligibility metric

Lightburn

Brookes

2015

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

It is known that the intelligibility of noisy speech can be improved by applying a binary-valued gain mask to a timefrequency representation of the speech. We present the SOBM, an oracle binary mask that maximises STOI, an objective speech intelligibility metric. We show how to determine the SOBM for a deterministic noise signal and also for a stochastic noise signal with a known power spectrum. We demonstrate that applying the SOBM to noisy speech results in a higher predicted intelligibility than is obtained with other masks and show that the stochastic version is robust to mismatch errors in SNR and noise spectrum.

show abstract

“…A popular family of intelligibility metrics are based on a correlation-comparison between the spectral envelopes of clean and degraded versions of the speech. One such metric, the Short-Time Objective Intelligibility Measure (STOI) [22], has been shown to have a high correlation with the intelligibility scores of both unenhanced and enhanced noisy speech signals [12,20].…”

Section: Introductionmentioning

confidence: 99%

A weighted STOI intelligibility metric based on mutual information

Lightburn

Brookes

2016

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

It is known that the information required for the intelligibility of a speech signal is distributed non-uniformly in time. In this paper we propose WSTOI, a modified version of STOI, a speech intelligibility metric. With WSTOI the contribution of each time-frequency cell is weighted by an estimate of its intelligibility content. This estimate is equal to the mutual information between two hypothetical signals at either end of a simplified model of human communication. Listening tests show that the modification improves the prediction accuracy of STOI at all performance levels on both long and short utterances. An improvement was observed across all tested noise types and suppression algorithms.

show abstract

Effects of noise suppression on intelligibility. II: An attempt to validate physical metrics

Cited by 7 publications

References 38 publications

ELO-SPHERES intelligibility prediction model for the Clarity Prediction Challenge 2022

ELO-SPHERES intelligibility prediction model for the Clarity Prediction Challenge 2022

SOBM - a binary mask for noisy speech that optimises an objective intelligibility metric

A weighted STOI intelligibility metric based on mutual information

Contact Info

Product

Resources

About