Effects of Silent Intervals on the Extraction of Human Frequency-Following Responses Using Non-Negative Matrix Factorization

Abstract

Source-Separation Non-Negative Matrix Factorization (SSNMF) is a mathematical algorithm recently developed to extract scalp-recorded frequency-following responses (FFRs) from noise. Despite its initial success, the effects of silent intervals on algorithm performance remain undetermined. Our purpose in this study was to determine the effects of silent intervals on the extraction of FFRs, which are electrophysiological responses that are commonly used to evaluate auditory processing and neuroplasticity in the human brain. We used an English vowel /i/ with a rising frequency contour to evoke FFRs in 23 normal-hearing adults. The stimulus had a duration of 150 ms, while the silent interval between the onset of one stimulus and the offset of the next one was also 150 ms. We computed FFR Enhancement and Noise Residue to estimate algorithm performance, while silent intervals were either included (i.e., the WithSI condition) or excluded (i.e., the WithoutSI condition) in our analysis. The FFR Enhancements and Noise Residues obtained in the WithoutSI condition were significantly better (p < .05) than those obtained in the WithSI condition. On average, the exclusion of silent intervals produced a 11.78% increment in FFR Enhancement and a 20.69% decrement in Noise Residue. These results not only quantify the effects of silent intervals on the extraction of human FFRs, but also provide recommendations for designing and improving the SSNMF algorithm in future research.

Keywords

electroencephalographic machine learning lexical tone frequency-following response silent interval non-negative matrix factorization algorithm performance

Get full access to this article

View all access options for this article.

References

Bermant

P. C.

(2021). BioCPPNet: Automatic bioacoustic source separation with deep neural networks. Scientific Reports, 11(1), 23502. https://doi.org/10.1038/s41598-021-02790-2

Chandrasekaran

Hornickel

Skoe

Nicol

Kraus

(2009). Context-dependent encoding in the human auditory brainstem relates to hearing speech in noise: Implications for developmental dyslexia. Neuron, 64(3), 311–319. https://doi.org/10.1016/j.neuron.2009.10.006

Cheng

F.-Y.

Gold

Smith

(2021). Rapid enhancement of subcortical neural responses to sine-wave speech. Frontiers in Neuroscience, 15, 747303. https://doi.org/10.3389/fnins.2021.747303

Cohen

M. X.

Analyzing neural time series data: Theory and practice. 1st ed. Cambridge, MA: The MIT Press; 2014. Available from: https://doi.org/10.7551/mitpress/9609.001.0001. Accessed June 27, 2023.

Cordeiro

F. P.

Weber

M. P. V.

Quintino

Skarzynska

Sanfins

M. D.

(2020). Assessment of learning disorder using the frequency following response: Systematic review. Journal of Hearing Science, 10(3), 9–18. https://doi.org/10.17430/JHS.2020.10.3.1

Font-Alaminos

Cornella

Costa-Faidella

Hervás

Leung

Rueda

Escera

(2020). Increased subcortical neural responses to repeating auditory stimulation in children with autism spectrum disorder. Biological Psychology, 149, 107807. https://doi.org/10.1016/j.biopsycho.2019.107807

Gnanateja

G. N.

Rupp

Llanos

Remick

Pernia

Sadagopan

Teichert

Abel

T. J.

Chandrasekaran

(2021). Frequency-following responses to speech sounds are highly conserved across species and contain cortical contributions. ENeuro, 8(6). ENEURO.0451-21.2021 https://doi.org/10.1523/ENEURO.0451-21.2021

Hart

Jeng

F.-C.

(2021). A demonstration of machine learning in detecting frequency following responses in American neonates. Perceptual and Motor Skills, 128(1), 48–58. https://doi.org/10.1177/0031512520960390

Hornickel

Kraus

(2013). Unstable representation of sound: A biological marker of dyslexia. The Journal of Neuroscience, 33(8), 3500–3504. https://doi.org/10.1523/jneurosci.4205-12.2013

10.

Jeng

F.-C.

Dickman

Montgomery-Reagan

Tong

Lin

C. D.

(2011). Cross-linguistic comparison of frequency-following responses to voice pitch in American and Chinese neonates and adults. Ear and Hearing, 32(6), 699–707. https://doi.org/10.1097/aud.0b013e31821cc0df

11.

Jeng

F.-C.

Lin

T.-H.

Hart

B. N.

Montgomery-Reagan

McDonald

(2023). Non-negative matrix factorization improves the efficiency of recording frequency-following responses in normal-hearing adults and neonates. International Journal of Audiology, 62(2), 688–698. https://doi.org/10.1080/14992027.2022.2071345

12.

Kraus

Lindley

Colegrove

Krizman

Otto-Meyer

Thompson

E. C.

White-Schwoch

(2017). The neural legacy of a single concussion. Neuroscience Letters, 646, 21–23. https://doi.org/10.1016/j.neulet.2017.03.008

13.

Kraus

Thompson

E. C.

Krizman

Cook

White-Schwoch

LaBella

C. R.

(2016). Auditory biological marker of concussion in children. Scientific Reports, 6, 39009. https://doi.org/10.1038/srep39009

14.

Krizman

Kraus

(2019). Analyzing the FFR: A tutorial for decoding the richness of auditory function. Hearing Research, 382, 107779. https://doi.org/10.1016/j.heares.2019.107779

15.

Lee

D. D.

Seung

H. S.

(1999). Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755), 788–791. https://doi.org/10.1038/44565

16.

Lemos

F. A.

da Silva Nunes

A. D.

de Souza Evangelista

C. K.

Escera

Taveira

K. V. M.

Balen

S. A.

(2021). Frequency-following response in newborns and infants: A systematic review of acquisition parameters. Journal of Speech, Language, and Hearing Research, 64(6), 2085–2102. https://doi.org/10.1044/2021_JSLHR-20-00639

17.

Lin

T.-H.

Fang

S.-H.

Tsao

(2017). Improving biodiversity assessment via unsupervised separation of biological sounds from long-duration recordings. Scientific Reports, 7(1). Article 1 https://doi.org/10.1038/s41598-017-04790-7

18.

Llanos

McHaney

J. R.

Schuerman

W. L.

H. G.

Leonard

M. K.

Chandrasekaran

(2020). Non-invasive peripheral nerve stimulation selectively enhances speech category learning in adults. NPJ Science of Learning, 5, 12. https://doi.org/10.1038/s41539-020-0070-0

19.

Llanos

Xie

Chandrasekaran

(2017). Hidden Markov modeling of frequency-following responses to Mandarin lexical tones. Journal of Neuroscience Methods, 291, 101–112. https://doi.org/10.1016/j.jneumeth.2017.08.010

20.

Llanos

Xie

Chandrasekaran

(2019). Biometric identification of listener identity from frequency following responses to speech. Journal of Neural Engineering, 16(5), 056004. https://doi.org/10.1088/1741-2552/ab1e01

21.

Llanos

Zhao

T. C.

Kuhl

P. K.

Chandrasekaran

(2022). The emergence of idiosyncratic patterns in the frequency-following response during the first year of life. JASA Express Letters, 2(5), 054401. https://doi.org/10.1121/10.0010493

22.

Otto-Meyer

Krizman

White-Schwoch

Kraus

(2018). Children with autism spectrum disorder have unstable neural responses to sound. Experimental Brain Research, 236(3), 733–743. https://doi.org/10.1007/s00221-017-5164-4

23.

Skoe

Kraus

(2010). Auditory brain stem response to complex sounds: A tutorial. Ear and Hearing, 31(3), 302–324. https://doi.org/10.1097/AUD.0b013e3181cdb272

24.

Vijayalakshmi

Purcell

D. W.

Aiken

S. J.

Parsa

Scollie

S. D.

(2015). Effect of stimulus level and bandwidth on speech-evoked envelope following responses in adults with normal hearing. Ear and Hearing, 36(6), 619–634. https://doi.org/10.1097/AUD.0000000000000188

25.

Wisdom

Tzinis

Erdogan

Weiss

R. J.

Wilson

Hershey

J. R.

Unsupervised sound separation using mixture invariant training; December 6-12, 2020; Online, Virtual Conference. NeurIPS; 2020, arXiv:2006.12701. Available from: http://arxiv.org/abs/2006.12701. Accessed August 24, 2022.

26.

Xie

Reetzke

Chandrasekaran

(2018). Taking attention away from the auditory modality: Context-dependent effects on early sensory encoding of speech. Neuroscience, 384, 64–75. https://doi.org/10.1016/j.neuroscience.2018.05.023

27.

Xie

Reetzke

Chandrasekaran

(2019). Machine learning approaches to analyze speech-evoked neurophysiological responses. Journal of Speech, Language, and Hearing Research, 62(3), 587–601. https://doi.org/10.1044/2018_jslhr-s-astm-18-0244

28.

H. G.

Xie

Reetzke

Dimakis

A. G.

Chandrasekaran

(2017). Vowel decoding from single-trial speech-evoked electrophysiological responses: A feature-based machine learning approach. Brain and Behavior, 7(6), Article e00665. https://doi.org/10.1002/brb3.665

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.19 MB

0.31 MB