Prediction of speech intelligibility based on a correlation metric in the envelope power spectrum domain

Helia Relaño-Iborra; Tobias May; Johannes Zaar; Christoph Scheidiger; Torsten Dau

Prediction of speech intelligibility based on a correlation metric in the envelope power spectrum domain

Helia Relaño-Iborra, Tobias May, Johannes Zaar, Christoph Scheidiger, Torsten Dau

Department of Electrical Engineering

Research output: Contribution to conference › Poster › Research

157 Downloads (Pure)

Abstract

A powerful tool to investigate speech perception is the use of speech intelligibility prediction models. Recently, a model was presented, termed correlation-based speechbased envelope power spectrum model (sEPSMcorr) [1], based on the auditory processing of the multi-resolution speech-based Envelope Power Spectrum Model (mr-sEPSM) [2], combined with the correlation back-end of the Short-Time Objective Intelligibility measure (STOI) [3]. The sEPSMcorr can accurately predict NH data for a broad range of listening conditions, e.g., additive noise, phase jitter and ideal binary mask processing.

Original language	English
Publication date	2017
Number of pages	1
Publication status	Published - 2017
Event	40th MidWinter Meeting of the Association for Research in Otolaryngology - Baltimore Marriott Waterfront , Baltimore, United States Duration: 11 Feb 2017 → 15 Feb 2017

Conference

Conference	40th MidWinter Meeting of the Association for Research in Otolaryngology
Location	Baltimore Marriott Waterfront
Country	United States
City	Baltimore
Period	11/02/2017 → 15/02/2017

Access to Document

ARO2017 final v2Final published version, 687 KB

Fingerprint Dive into the research topics of 'Prediction of speech intelligibility based on a correlation metric in the envelope power spectrum domain'. Together they form a unique fingerprint.

Cite this

@conference{4c04d7f4b491433a9275dedd50bf6174,

title = "Prediction of speech intelligibility based on a correlation metric in the envelope power spectrum domain",

abstract = "A powerful tool to investigate speech perception is the use of speech intelligibility prediction models. Recently, a model was presented, termed correlation-based speechbased envelope power spectrum model (sEPSMcorr) [1], based on the auditory processing of the multi-resolution speech-based Envelope Power Spectrum Model (mr-sEPSM) [2], combined with the correlation back-end of the Short-Time Objective Intelligibility measure (STOI) [3]. The sEPSMcorr can accurately predict NH data for a broad range of listening conditions, e.g., additive noise, phase jitter and ideal binary mask processing.",

author = "Helia Rela{\~n}o-Iborra and Tobias May and Johannes Zaar and Christoph Scheidiger and Torsten Dau",

year = "2017",

language = "English",

note = "40th MidWinter Meeting of the Association for Research in Otolaryngology ; Conference date: 11-02-2017 Through 15-02-2017",

}

Prediction of speech intelligibility based on a correlation metric in the envelope power spectrum domain. / Relaño-Iborra, Helia ; May, Tobias ; Zaar, Johannes; Scheidiger, Christoph; Dau, Torsten.

2017. Poster session presented at 40th MidWinter Meeting of the Association for Research in Otolaryngology, Baltimore, United States.

Research output: Contribution to conference › Poster › Research

TY - CONF

T1 - Prediction of speech intelligibility based on a correlation metric in the envelope power spectrum domain

AU - Relaño-Iborra, Helia

AU - May, Tobias

AU - Zaar, Johannes

AU - Scheidiger, Christoph

AU - Dau, Torsten

PY - 2017

Y1 - 2017

N2 - A powerful tool to investigate speech perception is the use of speech intelligibility prediction models. Recently, a model was presented, termed correlation-based speechbased envelope power spectrum model (sEPSMcorr) [1], based on the auditory processing of the multi-resolution speech-based Envelope Power Spectrum Model (mr-sEPSM) [2], combined with the correlation back-end of the Short-Time Objective Intelligibility measure (STOI) [3]. The sEPSMcorr can accurately predict NH data for a broad range of listening conditions, e.g., additive noise, phase jitter and ideal binary mask processing.

AB - A powerful tool to investigate speech perception is the use of speech intelligibility prediction models. Recently, a model was presented, termed correlation-based speechbased envelope power spectrum model (sEPSMcorr) [1], based on the auditory processing of the multi-resolution speech-based Envelope Power Spectrum Model (mr-sEPSM) [2], combined with the correlation back-end of the Short-Time Objective Intelligibility measure (STOI) [3]. The sEPSMcorr can accurately predict NH data for a broad range of listening conditions, e.g., additive noise, phase jitter and ideal binary mask processing.

M3 - Poster

T2 - 40th MidWinter Meeting of the Association for Research in Otolaryngology

Y2 - 11 February 2017 through 15 February 2017

ER -