Influence of environmental background noise on speech quality assessments task in crowdsourcing microtask platform

2017 ◽  
Vol 141 (5) ◽  
pp. 3909-3910
Author(s):  
Babak Naderi ◽  
Sebastian Möller ◽  
Frank Neubert ◽  
Victor Höller ◽  
Friedemann Köster ◽  
...  
Keyword(s):  
Background Noise ◽  
Speech Quality ◽  
Environmental Background ◽  
Quality Assessments

scholarly journals Towards speech quality assessment using a crowdsourcing approach: evaluation of standardized methods

2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Babak Naderi ◽  
Rafael Zequeira Jiménez ◽  
Matthias Hirth ◽  
Sebastian Möller ◽  
Florian Metzger ◽  
...  
Keyword(s):  
Quality Assessment ◽  
Ecological Validity ◽  
Speech Quality ◽  
Standard Laboratory ◽  
New Paradigm ◽  
Speech Quality Assessment ◽  
Practical Guidelines ◽  
Quality Assessments ◽  
Comparability Of Results

AbstractSubjective speech quality assessment has traditionally been carried out in laboratory environments under controlled conditions. With the advent of crowdsourcing platforms tasks, which need human intelligence, can be resolved by crowd workers over the Internet. Crowdsourcing also offers a new paradigm for speech quality assessment, promising higher ecological validity of the quality judgments at the expense of potentially lower reliability. This paper compares laboratory-based and crowdsourcing-based speech quality assessments in terms of comparability of results and efficiency. For this purpose, three pairs of listening-only tests have been carried out using three different crowdsourcing platforms and following the ITU-T Recommendation P.808. In each test, listeners judge the overall quality of the speech sample following the Absolute Category Rating procedure. We compare the results of the crowdsourcing approach with the results of standard laboratory tests performed according to the ITU-T Recommendation P.800. Results show that in most cases, both paradigms lead to comparable results. Notable differences are discussed with respect to their sources, and conclusions are drawn that establish practical guidelines for crowdsourcing-based speech quality assessment.

Directed Searching Optimization-Based Speech Enhancement Technique

2020 ◽  
Vol 19 (04) ◽  
pp. 2050035
Author(s):  
Sandeep Kumar
Keyword(s):  
Speech Enhancement ◽  
Background Noise ◽  
Optimization Problems ◽  
Speech Quality ◽  
Directed Search ◽  
Least Mean Square ◽  
Swarm Optimization ◽  
Search Optimization ◽  
Enhancement Method ◽  
Echo Suppression

In general, the background noise degrades the speech quality. Thus, the intelligibility of the speech can be enhanced by mitigating the effects of background noise and echo suppression. So, speech enhancement can also be viewed as one of the optimization problems. In this work, directed search optimization (DSO) method is used to enhance the speech quality which is originally degraded. The performance of DSO-based speech enhancement method is compared with particle swarm optimization (PSO) and least mean square (LMS)-based methods in terms of output average segmental SNR and speech quality. From the experimental results, it was observed that the output spectrogram, output ASSNR and speech quality using DSO algorithm are far better as compared to PSO and LMS-based methods. Moreover, DSO-based method is computationally less complex as compared to the PSO-based method.

Speech Naturalness and Prolonged-Speech Treatments for Stuttering

1992 ◽  
Vol 35 (2) ◽  
pp. 274-282 ◽  
Author(s):  
Mark Onslow ◽  
Brett Hayes ◽  
Leanne Hutchins ◽  
Denis Newman
Keyword(s):  
Treatment Program ◽  
Free Speech ◽  
Significant Positive Correlation ◽  
Speech Quality ◽  
Positive Correlation ◽  
Empirical Information ◽  
Scale Scores ◽  
Quality Assessments ◽  
Speech Naturalness

It is well known that unusual speech quality may result from stuttering treatments that are based on prolonged speech. However, empirical information concerning the speech quality associated with those treatments is lacking. The present study was designed to contribute such empirical information. Results indicated that speech quality assessments of posttreatment clients, using Martin, Haroldson, and Triden's (1984) speech naturalness scale, gave similar results regardless of whether they were based on monologues or conversations. The speech quality of those clients remained stable at the conclusion of their treatment program. Further, there was a significant, positive correlation between pretreatment speech measures and measures of speech naturalness made after the establishment of stutter-free speech. The subjects whose pretreatment stuttering was the most severe had posttreatment speech naturalness scores that were more than two scale values worse than the subjects whose pretreatment stuttering was the least severe. Speech naturalness scale scores are presented for nonstutterers and posttreatment stutterers and these data are compared with existing findings.

Sign in / Sign up

Export Citation Format

Share Document