Speech intelligibility prediction using a Neurogram Similarity Index Measure

By Andrew Hines, Naomi Harte. 2012

103 citations recorded by the source corpus.

Discharge patterns produced by fibres from normal and impaired auditory nerves in response to speech and other complex sounds can be discriminated subjectively through visual inspection. Similarly, responses from auditory nerves where speech is presented at diminishing sound levels progressively deteriorate from those at normal listening levels. This paper presents a Neurogram Similarity Index Measure (NSIM) that automates this inspection process, and translates the response pattern differences into a bounded discrimination metric. Performance intensity functions can be used to provide additional information over measurement of speech reception threshold and maximum phoneme recognition by plotting a test subject's recognition probability over a range of sound intensities. A computational model of the auditory periphery was used to replace the human subject and develop a methodology that simulates a real listener test. The newly developed NSIM is used to evaluate the model outputs in response to Consonant-Vowel-Consonant (CVC) word lists and produce phoneme discrimination scores. The simulated results are rigorously compared to those from normal hearing subjects in both quiet and noise conditions. The accuracy of the tests and the minimum number of word lists necessary for repeatable results is established and the results are compared to predictions using the speech intelligibility index (SII). The experiments demonstrate that the proposed simulated performance intensity function (SPIF) produces results with confidence intervals within the human error bounds expected with real listener tests. This work represents an important step in validating the use of auditory nerve models to predict speech intelligibility.

Subfields: Cognitive Neuroscience, Speech and Hearing, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Speech and Hearing

In Signal Processing

Citations in the corpus

ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metric (2020, methodology): “This requires that a new SVR model is trained to map the frequency band NSIM to MOS using libsvm [27].”
ViSQOL: an objective speech quality model (2015, methodology): “SSIM was further tuned, and it was established that the contrast component provided negligible value when comparing neurograms and that closer fitting to listener test data occurred using only a luminance and structural comparison [33].”
ViSQOL: The Virtual Speech Quality Objective Listener (2012, methodology): “It should be noted that prior experience measuring speech similarity with NSIM [3] found a practical peak similarity”
Objective Assessment of Perceptual Audio Quality Using ViSQOLAudio (2017, methodology): “The NSIM of a reference and degraded patch is described as: NSIM ( Pri , P d j ) = l ( Pri , P d j , c1 ) · s ( Pri , P d j , c3 ) (2) where Pri is the reference patch, P d i is the degraded patch, l is luminosity and s is structure.”
AMBIQUAL - a full reference objective quality metric for ambisonic spatial audio (2018, methodology): “NSIM [19], a similarity measure that compares the similarity of signals by aligning and evaluating the similarity across time and frequency bands using a spectrogram-based comparison.”
Measuring and monitoring speech quality for voice over IP with POLQA, viSQOL and p.563 (2015, methodology): “[21] A. Hines, E. Gillen, J. Skoglund, A. Kokaram, and N. Harte, “Visqolaudio: An objective audio quality metric for low bitrate codecs,” The Journal of the Acoustical Society of America, vol. 137:6, June 2015.”
Bitrate classification of twice-encoded audio using objective quality features (2016, methodology): “It uses a Neurogram Similarity Index Measure (NSIM) [12] to compare spectrograms across critical frequency bands from 50 Hz to 16000 Hz and patches consisting of 30 0.016 s time frames and outputs a quality score between 0 and 1, with 1 signifying perfect quality.”
Robustness of speech quality metrics to background noise and network degradations: Comparing ViSQOL, PESQ and POLQA (2013, unknown): “3697978-1-4799-0356-6/13/$31.00 ©2013 IEEE ICASSP 2013”