2019
DOI: 10.1109/taslp.2018.2882738
|View full text |Cite
|
Sign up to set email alerts
|

Subjective Evaluation of a Noise-Reduced Training Target for Deep Neural Network-Based Speech Enhancement

Abstract: Speech enhancement systems aim to improve the quality and intelligibility of noisy speech. In this study, we compare two speech enhancement systems based on deep neural networks. The speech intelligibility and quality of both systems was evaluated subjectively, by a Speech Recognition Test based on Hagerman sentences and a translation of the ITU-T P.835 recommendation, respectively. Results were compared with the objective measures STOI and POLQA. Neither STOI nor POLQA reliably predicted subjective results. W… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

1
19
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
8
1
1

Relationship

0
10

Authors

Journals

citations
Cited by 26 publications
(20 citation statements)
references
References 30 publications
1
19
0
Order By: Relevance
“…[13][14][15]53 In the current trend, machine learning approaches 16 have proved its great strength in speech intelligibility improvement for CI users, 17 NH listeners, HI listeners, [18][19][20] and medical signals. 6,[21][22][23] Normally, based on the incoming signal, gain function for noise and speech statistics is estimated. Nonetheless, the optimal gain function was estimated using the traditional machine learning approaches by means of incorporating prior knowledge of speech and noise patterns.…”
Section: Introductionmentioning
confidence: 99%
“…[13][14][15]53 In the current trend, machine learning approaches 16 have proved its great strength in speech intelligibility improvement for CI users, 17 NH listeners, HI listeners, [18][19][20] and medical signals. 6,[21][22][23] Normally, based on the incoming signal, gain function for noise and speech statistics is estimated. Nonetheless, the optimal gain function was estimated using the traditional machine learning approaches by means of incorporating prior knowledge of speech and noise patterns.…”
Section: Introductionmentioning
confidence: 99%
“…This paper uses the amplitude spectrum under two hypothetical conditions to carry out simulation experiments, and compares the results with the ideal state, we find the speech intelligibility has indeed improved through the objective evaluation index of speech intelligibility, and the improvement of the methods has been successfully applied to reality. In recent years, deep neural network algorithms have also been applied to the field of speech enhancement [16]. Speech enhancement algorithms based on improved speech intelligibility also have good development prospects [17,18].…”
Section: Resultsmentioning
confidence: 99%
“…For these three indicators, the higher the value is, the higher the speech quality. Some scholars think that objective evaluation cannot replace subjective evaluation [43]. So, in addition to the objective measurements, subjective listening tests are performed to evaluate the perceptual quality of enhanced speech signals.…”
Section: B Evaluation Indexesmentioning
confidence: 99%