Blind Room Volume Estimation from Single-channel Noisy Speech

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


  • A. F. Genovese
  • H. Gamper
  • Ville Pulkki

  • N. Raghuvanshi
  • I. J. Tashev

Research units

  • New York University
  • Microsoft Research


Recent work on acoustic parameter estimation indicates that geometric room volume can be useful for modeling the character of an acoustic environment. However, estimating volume from audio signals remains a challenging problem. Here we propose using a convolutional neural network model to estimate the room volume blindly from reverberant single-channel speech signals in the presence of noise. The model is shown to produce estimates within approximately a factor of two to the true value, for rooms ranging in size from small offices to large concert halls.


Original languageEnglish
Title of host publicationICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publication statusPublished - 1 May 2019
MoE publication typeA4 Article in a conference publication
EventIEEE International Conference on Acoustics, Speech, and Signal Processing - Brighton, United Kingdom
Duration: 12 May 201917 May 2019
Conference number: 44

Publication series

NameProceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing
ISSN (Print)1520-6149
ISSN (Electronic)2379-190X


ConferenceIEEE International Conference on Acoustics, Speech, and Signal Processing
Abbreviated titleICASSP
CountryUnited Kingdom

    Research areas

  • Acoustics, Volume measurement, Training, Solid modeling, Noise measurement, Data models, Acoustic measurements, Room acoustics, room size, non-intrusive parameter estimation, signal processing, convolutional neural network

Download statistics

No data available

ID: 33975571