Tags

Type your tag names separated by a space and hit enter

Large-scale training to increase speech intelligibility for hearing-impaired listeners in novel noises.
J Acoust Soc Am. 2016 05; 139(5):2604.JA

Abstract

Supervised speech segregation has been recently shown to improve human speech intelligibility in noise, when trained and tested on similar noises. However, a major challenge involves the ability to generalize to entirely novel noises. Such generalization would enable hearing aid and cochlear implant users to improve speech intelligibility in unknown noisy environments. This challenge is addressed in the current study through large-scale training. Specifically, a deep neural network (DNN) was trained on 10 000 noises to estimate the ideal ratio mask, and then employed to separate sentences from completely new noises (cafeteria and babble) at several signal-to-noise ratios (SNRs). Although the DNN was trained at the fixed SNR of - 2 dB, testing using hearing-impaired listeners demonstrated that speech intelligibility increased substantially following speech segregation using the novel noises and unmatched SNR conditions of 0 dB and 5 dB. Sentence intelligibility benefit was also observed for normal-hearing listeners in most noisy conditions. The results indicate that DNN-based supervised speech segregation with large-scale training is a very promising approach for generalization to new acoustic environments.

Authors+Show Affiliations

Department of Computer Science and Engineering, The Ohio State University, Columbus, Ohio 43210, USA.Department of Computer Science and Engineering, The Ohio State University, Columbus, Ohio 43210, USA.Department of Speech and Hearing Science, The Ohio State University, Columbus, Ohio 43210, USA.Department of Computer Science and Engineering, The Ohio State University, Columbus, Ohio 43210, USA.Department of Speech and Hearing Science, The Ohio State University, Columbus, Ohio 43210, USA.

Pub Type(s)

Journal Article
Research Support, N.I.H., Extramural
Research Support, U.S. Gov't, Non-P.H.S.

Language

eng

PubMed ID

27250154

Citation

Chen, Jitong, et al. "Large-scale Training to Increase Speech Intelligibility for Hearing-impaired Listeners in Novel Noises." The Journal of the Acoustical Society of America, vol. 139, no. 5, 2016, p. 2604.
Chen J, Wang Y, Yoho SE, et al. Large-scale training to increase speech intelligibility for hearing-impaired listeners in novel noises. J Acoust Soc Am. 2016;139(5):2604.
Chen, J., Wang, Y., Yoho, S. E., Wang, D., & Healy, E. W. (2016). Large-scale training to increase speech intelligibility for hearing-impaired listeners in novel noises. The Journal of the Acoustical Society of America, 139(5), 2604. https://doi.org/10.1121/1.4948445
Chen J, et al. Large-scale Training to Increase Speech Intelligibility for Hearing-impaired Listeners in Novel Noises. J Acoust Soc Am. 2016;139(5):2604. PubMed PMID: 27250154.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Large-scale training to increase speech intelligibility for hearing-impaired listeners in novel noises. AU - Chen,Jitong, AU - Wang,Yuxuan, AU - Yoho,Sarah E, AU - Wang,DeLiang, AU - Healy,Eric W, PY - 2016/6/3/entrez PY - 2016/6/3/pubmed PY - 2018/7/4/medline SP - 2604 EP - 2604 JF - The Journal of the Acoustical Society of America JO - J Acoust Soc Am VL - 139 IS - 5 N2 - Supervised speech segregation has been recently shown to improve human speech intelligibility in noise, when trained and tested on similar noises. However, a major challenge involves the ability to generalize to entirely novel noises. Such generalization would enable hearing aid and cochlear implant users to improve speech intelligibility in unknown noisy environments. This challenge is addressed in the current study through large-scale training. Specifically, a deep neural network (DNN) was trained on 10 000 noises to estimate the ideal ratio mask, and then employed to separate sentences from completely new noises (cafeteria and babble) at several signal-to-noise ratios (SNRs). Although the DNN was trained at the fixed SNR of - 2 dB, testing using hearing-impaired listeners demonstrated that speech intelligibility increased substantially following speech segregation using the novel noises and unmatched SNR conditions of 0 dB and 5 dB. Sentence intelligibility benefit was also observed for normal-hearing listeners in most noisy conditions. The results indicate that DNN-based supervised speech segregation with large-scale training is a very promising approach for generalization to new acoustic environments. SN - 1520-8524 UR - https://www.unboundmedicine.com/medline/citation/27250154/Large_scale_training_to_increase_speech_intelligibility_for_hearing_impaired_listeners_in_novel_noises_ L2 - https://doi.org/10.1121/1.4948445 DB - PRIME DP - Unbound Medicine ER -