Investigation of an Encoder-Decoder LSTM Model on the Enhancement of Speech Intelligibility in Noise for Hearing Impaired Listeners
×
Cite This
Citation & Abstract
I. Thoidis, L. Vrysis, K. Pastiadis, K. Markou, and G. Papanikolaou, "Investigation of an Encoder-Decoder LSTM Model on the Enhancement of Speech Intelligibility in Noise for Hearing Impaired Listeners," Paper 10206, (2019 March.). doi:
I. Thoidis, L. Vrysis, K. Pastiadis, K. Markou, and G. Papanikolaou, "Investigation of an Encoder-Decoder LSTM Model on the Enhancement of Speech Intelligibility in Noise for Hearing Impaired Listeners," Paper 10206, (2019 March.). doi:
Abstract: Hearing impaired (HI) listeners often struggle to follow conversations when exposed in a complex acoustic environment. This is partly due to the reduced ability in recovering the target speech Temporal Envelope (ENV) cues from Temporal Fine Structure (TFS). This study investigates the enhancement of speech intelligibility in HI listeners by processing the ENV of speech signals corrupted by real-world environmental noise. An Encoder-Decoder Long Short Term Memory (LSTM) model is exploited after perceptually motivated processing stages to compensate for the important ENV characteristics of comprehensible speech for hearing impairment. The computational model is evaluated using the Short-Time Objective Intelligibility (STOI) measure for speech intelligibility. Finally, results indicate a 6% improvement in the mean STOI measure across different SNR values.
@article{thoidis2019investigation,
author={thoidis, iordanis and vrysis, lazaros and pastiadis, konstantinos and markou, konstantinos and papanikolaou, george},
journal={journal of the audio engineering society},
title={investigation of an encoder-decoder lstm model on the enhancement of speech intelligibility in noise for hearing impaired listeners},
year={2019},
volume={},
number={},
pages={},
doi={},
month={march},}
@article{thoidis2019investigation,
author={thoidis, iordanis and vrysis, lazaros and pastiadis, konstantinos and markou, konstantinos and papanikolaou, george},
journal={journal of the audio engineering society},
title={investigation of an encoder-decoder lstm model on the enhancement of speech intelligibility in noise for hearing impaired listeners},
year={2019},
volume={},
number={},
pages={},
doi={},
month={march},
abstract={hearing impaired (hi) listeners often struggle to follow conversations when exposed in a complex acoustic environment. this is partly due to the reduced ability in recovering the target speech temporal envelope (env) cues from temporal fine structure (tfs). this study investigates the enhancement of speech intelligibility in hi listeners by processing the env of speech signals corrupted by real-world environmental noise. an encoder-decoder long short term memory (lstm) model is exploited after perceptually motivated processing stages to compensate for the important env characteristics of comprehensible speech for hearing impairment. the computational model is evaluated using the short-time objective intelligibility (stoi) measure for speech intelligibility. finally, results indicate a 6% improvement in the mean stoi measure across different snr values.},}
TY - paper
TI - Investigation of an Encoder-Decoder LSTM Model on the Enhancement of Speech Intelligibility in Noise for Hearing Impaired Listeners
SP -
EP -
AU - Thoidis, Iordanis
AU - Vrysis, Lazaros
AU - Pastiadis, Konstantinos
AU - Markou, Konstantinos
AU - Papanikolaou, George
PY - 2019
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - March 2019
TY - paper
TI - Investigation of an Encoder-Decoder LSTM Model on the Enhancement of Speech Intelligibility in Noise for Hearing Impaired Listeners
SP -
EP -
AU - Thoidis, Iordanis
AU - Vrysis, Lazaros
AU - Pastiadis, Konstantinos
AU - Markou, Konstantinos
AU - Papanikolaou, George
PY - 2019
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - March 2019
AB - Hearing impaired (HI) listeners often struggle to follow conversations when exposed in a complex acoustic environment. This is partly due to the reduced ability in recovering the target speech Temporal Envelope (ENV) cues from Temporal Fine Structure (TFS). This study investigates the enhancement of speech intelligibility in HI listeners by processing the ENV of speech signals corrupted by real-world environmental noise. An Encoder-Decoder Long Short Term Memory (LSTM) model is exploited after perceptually motivated processing stages to compensate for the important ENV characteristics of comprehensible speech for hearing impairment. The computational model is evaluated using the Short-Time Objective Intelligibility (STOI) measure for speech intelligibility. Finally, results indicate a 6% improvement in the mean STOI measure across different SNR values.
Hearing impaired (HI) listeners often struggle to follow conversations when exposed in a complex acoustic environment. This is partly due to the reduced ability in recovering the target speech Temporal Envelope (ENV) cues from Temporal Fine Structure (TFS). This study investigates the enhancement of speech intelligibility in HI listeners by processing the ENV of speech signals corrupted by real-world environmental noise. An Encoder-Decoder Long Short Term Memory (LSTM) model is exploited after perceptually motivated processing stages to compensate for the important ENV characteristics of comprehensible speech for hearing impairment. The computational model is evaluated using the Short-Time Objective Intelligibility (STOI) measure for speech intelligibility. Finally, results indicate a 6% improvement in the mean STOI measure across different SNR values.
Authors:
Thoidis, Iordanis; Vrysis, Lazaros; Pastiadis, Konstantinos; Markou, Konstantinos; Papanikolaou, George
Affiliation:
Aristotle University of Thessaloniki, Thessaloniki, Greece
AES Convention:
146 (March 2019)
Paper Number:
10206
Publication Date:
March 10, 2019Import into BibTeX
Subject:
Poster Session 4
Permalink:
http://www.aes.org/e-lib/browse.cfm?elib=20339