A Speech Intelligibility Estimation Method Using a Non-reference Feature Set
T Sakano, Y Kobayashi, K Kondo - IEICE TRANSACTIONS on …, 2015 - search.ieice.org
We proposed and evaluated a speech intelligibility estimation method that does not require
a clean speech reference signal. The propose method uses the features defined in the ITU-T …
a clean speech reference signal. The propose method uses the features defined in the ITU-T …
[PDF][PDF] Single-ended estimation of speech intelligibility using the ITU p. 563 feature set.
T Sakano, Y Kobayashi, K Kondo - INTERSPEECH, 2014 - isca-archive.org
We investigated a single-ended speech intelligibility estimation method that does not require
clean speech reference signal, using the features defined in the ITU-T standard P. 563. We …
clean speech reference signal, using the features defined in the ITU-T standard P. 563. We …
Estimation of speech intelligibility using objective measures
K Kondo - Applied Acoustics, 2013 - Elsevier
In this paper, a method to estimate the subjective speech intelligibility scores of the
Japanese DRT speech intelligibility test using some objective measures is proposed and …
Japanese DRT speech intelligibility test using some objective measures is proposed and …
Estimation of speech intelligibility using speech recognition systems
Y Takano, K Kondo - IEICE TRANSACTIONS on Information and …, 2010 - search.ieice.org
We attempted to estimate subjective scores of the Japanese Diagnostic Rhyme Test (DRT),
a two-to-one forced selection speech intelligibility test. We used automatic speech …
a two-to-one forced selection speech intelligibility test. We used automatic speech …
Learning to Predict Speech Intelligibility from Speech Distortions
P Kuriakose - International Conference on Speech and Computer, 2023 - Springer
This paper discusses a learning approach to predict speech intelligibility in a non-intrusive
manner. The difference in the objective intelligibility of a speech signal and its distorted …
manner. The difference in the objective intelligibility of a speech signal and its distorted …
Non-intrusive speech intelligibility assessment
We present NISI, a novel non-intrusive speech intelligibility assessment method based on
feature extraction and a binary tree regression model. A training method using the intrusive …
feature extraction and a binary tree regression model. A training method using the intrusive …
[引用][C] Improving accuracy of estimated speech intelligibility scores by speech recognizers using multi-condition noise-adapted models
K Kondo - INTER-NOISE and NOISE-CON Congress and …, 2011 - ingentaconnect.com
We attempted to improve the estimated intelligibility scores of the Japanese Diagnostic
Rhyme Test (DRT), a two-to-one forced selection speech intelligibility test, using automatic …
Rhyme Test (DRT), a two-to-one forced selection speech intelligibility test, using automatic …
A data-driven speech intelligibility assessment method using sum-sorted spectrogram feature
J Xupeng, L Dongmei - 2016 IEEE 13th International …, 2016 - ieeexplore.ieee.org
A novel data-driven non-intrusive method to assess speech intelligibility is proposed. The
approach uses a new segment-based feature called Sum-Sorted Spectrogram (SSS) and a …
approach uses a new segment-based feature called Sum-Sorted Spectrogram (SSS) and a …
[图书][B] On non-reference speech intelligibility estimation using DNN noise reduction
H Takahashi, K Kondo - 2019 - publications.rwth-aachen.de
Methods for estimating speech intelligibility are classified into two types. One is the full
reference method that estimates the subjective evaluation values using both degraded …
reference method that estimates the subjective evaluation values using both degraded …
A non-intrusive speech intelligibility estimation method based on deep learning using autoencoder features
Y Kim, D Yun, H Lee, SH Choi - IEICE TRANSACTIONS on …, 2020 - search.ieice.org
This paper presents a deep learning-based non-intrusive speech intelligibility estimation
method using bottleneck features of autoencoder. The conventional standard non-intrusive …
method using bottleneck features of autoencoder. The conventional standard non-intrusive …