The analysis of conversational signal-to-noise ratios (SNRs) measured in real-world scenarios can provide vital insight into people's communicative strategies and difficulties and guide development of hearing devices. However, measuring SNRs accurately and realistically is challenging in typical recording conditions, where only a mixture of sound sources is captured. This study introduces a novel method for realistic in situ SNR estimation, where the speech signal of a person in natural conversation is captured by a cheek-mounted microphone, adjusted for free-field conditions, and convolved with a measured impulse response to estimate the clean speech component at the receiver. A microphone near the receiver computes the noise-only component by applying a voice activity detector. Obtained SNR values are analyzed using in situ recordings of a real-world workspace meeting. It is shown that the temporal resolution is increased, and fluctuations in the speech level are more accurately tracked compared to a typical spectral-subtraction-derived method. The application of the proposed SNR estimation method may be valuable for compensation procedures in hearing instruments that take conversational dynamics into account.
Skip Nav Destination
Article navigation
March 2019
Meeting abstract. No PDF available.
March 01 2019
A method for conversational signal-to-noise ratio estimation in real-world sound scenarios
Naim Mansour;
Naim Mansour
Hearing Systems, Dept. of Health Technol., Tech. Univ. of Denmark, Ørsteds Plads, Bldg. 352, Kongens Lyngby 2800, Denmark, [email protected]
Search for other works by this author on:
Márton Marschall;
Márton Marschall
Hearing Systems, Dept. of Health Technol., Tech. Univ. of Denmark, Kgs. Lyngby, Denmark
Search for other works by this author on:
Tobias May;
Tobias May
Hearing Systems, Dept. of Health Technol., Tech. Univ. of Denmark, Kgs. Lyngby, Denmark
Search for other works by this author on:
Adam Westermann;
Adam Westermann
Widex A/S, Lynge, Denmark
Search for other works by this author on:
Torsten Dau
Torsten Dau
Hearing Systems, Dept. of Health Technol., Tech. Univ. of Denmark, Kgs. Lyngby, Denmark
Search for other works by this author on:
J. Acoust. Soc. Am. 145, 1873 (2019)
Citation
Naim Mansour, Márton Marschall, Tobias May, Adam Westermann, Torsten Dau; A method for conversational signal-to-noise ratio estimation in real-world sound scenarios. J. Acoust. Soc. Am. 1 March 2019; 145 (3_Supplement): 1873. https://doi.org/10.1121/1.5101769
Download citation file:
Citing articles via
All we know about anechoic chambers
Michael Vorländer
A survey of sound source localization with deep learning methods
Pierre-Amaury Grumiaux, Srđan Kitić, et al.
Does sound symbolism need sound?: The role of articulatory movement in detecting iconicity between sound and meaning
Mutsumi Imai, Sotaro Kita, et al.
Related Content
A method for realistic, conversational signal-to-noise ratio estimation
J. Acoust. Soc. Am. (March 2021)
Speech intelligibility in a realistic virtual sound environment
J. Acoust. Soc. Am. (April 2021)
Guided ecological momentary assessment in real and virtual sound environments
J. Acoust. Soc. Am. (October 2021)
Didjeridu acoustics: A review
J. Acoust. Soc. Am. (October 2023)
Correlation of biological and acoustical measurements of the endangered Golden Cheeked Warbler with applications of machine learning
J Acoust Soc Am (September 2018)