Imperial College London


Faculty of EngineeringDepartment of Electrical and Electronic Engineering

Research Associate







809Electrical EngineeringSouth Kensington Campus






BibTex format

author = {Eaton, J and Gaubitch, ND and Moore, AH and Naylor, PA},
title = {Proceedings of the ACE Challenge Workshop - a satellite event of IEEE-WASPAA (2015)},
type = {OTHER},
url = {},
year = {2015}

RIS format (EndNote, RefMan)

AB - Several established parameters and metrics have been used to characterize theacoustics of a room. The most important are the Direct-To-Reverberant Ratio(DRR), the Reverberation Time (T60) and the reflection coefficient. Theacoustic characteristics of a room based on such parameters can be used topredict the quality and intelligibility of speech signals in that room.Recently, several important methods in speech enhancement and speechrecognition have been developed that show an increase in performance comparedto the predecessors but do require knowledge of one or more fundamentalacoustical parameters such as the T60. Traditionally, these parameters havebeen estimated using carefully measured Acoustic Impulse Responses (AIRs).However, in most applications it is not practical or even possible to measurethe acoustic impulse response. Consequently, there is increasing researchactivity in the estimation of such parameters directly from speech and audiosignals. The aim of this challenge was to evaluate state-of-the-art algorithmsfor blind acoustic parameter estimation from speech and to promote the emergingarea of research in this field. Participants evaluated their algorithms for T60and DRR estimation against the 'ground truth' values provided with thedata-sets and presented the results in a paper describing the method used.
AU - Eaton,J
AU - Gaubitch,ND
AU - Moore,AH
AU - Naylor,PA
PY - 2015///
TI - Proceedings of the ACE Challenge Workshop - a satellite event of IEEE-WASPAA (2015)
UR -
ER -