Speech signal denoising with wavelet-transforms and the mean opinion score characterizing the filtering quality

2016 ◽  
Author(s):  
Alauldeen S. Yaseen ◽  
Alexey N. Pavlov ◽  
Alexander E. Hramov
Keyword(s):  
Speech Signal ◽  
Wavelet Transforms ◽  
Mean Opinion Score ◽  
Signal Denoising ◽  
Opinion Score ◽  
The Mean

scholarly journals Enhancement of the perceptive quality of the noisy speech signal by using of DFF-FBC algorithm

2009 ◽  
Vol 22 (3) ◽  
pp. 391-404
Author(s):  
Zoran Milivojevic ◽  
Dragisa Balaneskovic
Keyword(s):  
Speech Signal ◽  
Mean Opinion Score ◽  
Signal Quality ◽  
Test Results ◽  
Frequency Filtering ◽  
Noisy Speech ◽  
Voice Signal ◽  
Opinion Score

This paper presents an algorithm for enhancement of the noisy speech signal quality. This algorithm is based on the dissonant frequency filtering (DFF), F#, B and C# in relation to the frequency of the primary tone C (DFF-FBC algorithm). By means of the subjective Mean Opinion Score (MOS) test, the effect of the enhancement of the speech signal quality was analyzed. The analysis of the MOS test results, presented in the second part of this paper, points out to the enhancement of the noisy speech signal quality in the presence of superimposed noises. Especially good results have been found with Husky Voice signal. .

scholarly journals Rancang Bangun Aplikasi Pelaporan Keadaan Darurat di Kota Mataram(Studi Kasus Nomor Panggilan Darurat 112)

2020 ◽  
Vol 4 (1) ◽  
pp. 36-44
Author(s):  
I Made Dwi Mahardika ◽  
Royana Afwani ◽  
Moh. Ali Albar
Keyword(s):  
Reporting System ◽  
Score Test ◽  
Mean Opinion Score ◽  
Emergency Call ◽  
Web Pages ◽  
The Public ◽  
Opinion Score ◽  
Black Box Testing ◽  
The Mean ◽  
Call Number

Emergencies can occur anywhere and anytime, where handling these emergencies must be done quickly. This research was conducted to design and build an emergency reporting system in the city of Mataram. The emergency reporting system that was built took the workflow from the emergency call number 112. The system will be used by 4 users namely the citizen as a emergency reporter, call taker emergency call number 112 from Diskominfo as an information processor, admin as a call taker information processor and units such as ambulances and firefighters as the action takers of the submitted report. The system runs in 2 platforms, namely the web pages used by call takers and Android, which are used by the public and action units. The system is tested using the mean opinion score and black box testing. The results obtained by using the mean opinion score test is 3.6 or the fair category.

scholarly journals Rancang Bangun Sistem Informasi TOEFL pada Pusat Bahasa Universitas Mataram

2019 ◽  
Vol 1 (2) ◽  
Author(s):  
Imam Tantowi
Keyword(s):  
System Development ◽  
Mean Opinion Score ◽  
Test Results ◽  
Process Scheduling ◽  
Registration System ◽  
Existing Problems ◽  
Opinion Score ◽  
The Mean ◽  
Waterfall Model ◽  
The University

This research was conducted based on existing problems in the registration system, scheduling, and announcement of the results of the TOEFL test at the Language Center of the University of Mataram. Where registration, scheduling, and the announcement of TOEFL test results are done manually which requires prospective participants to register directly at the language center of the University of Mataram. This system is expected to simplify the registration process, scheduling, displaying available quotas and checking TOEFL test results. This system was built using a CodeIgniter framework, XAMPP as a web server and MySQL PhpMyadmin as its database server and built with the waterfall model as a system development method. This system is tested by the black box method and user interface testing will be used subjectively testing using the mean opinion score (MOS) by involving several respondents. Based on the test results of the Mean Opinion Score method, it can be concluded that 66.1% of the respondents agreed and 33% of the respondents strongly agreed with the TOEFL Information System Design in UNRAM.

scholarly journals Analisis Perbandingan Mean Opinion Score Aplikasi VoIP Facebook Messenger dan Google Hangouts menggunakan Metode E-Model pada Jaringan LTE

2018 ◽  
Vol 6 (3) ◽  
pp. 379
Author(s):  
RAMADHINA FITRIYANTI ◽  
LINDAWATI LINDAWATI ◽  
ARYANTI ARYANTI
Keyword(s):  
Network Topology ◽  
Packet Loss ◽  
User Satisfaction ◽  
Mean Opinion Score ◽  
Test Results ◽  
Lte Networks ◽  
Opinion Score ◽  
Call Process ◽  
The Mean

ABSTRAKPenelitian ini membahas mengenai perbandingan kualitas layanan dua aplikasi VoIP yaitu Facebook Messenger dan Google Hangouts pada jaringan LTE. Kualitas layanan dua aplikasi tersebut ditinjau menggunakan Mean Opinion Score dengan metode objektif yaitu, E-Model. Nilai MOS kedua aplikasi didapatkan dengan menjalankan simulasi menggunakan GNS3 yang berfungsi untuk mensimulasikan topologi jaringan dengan menggunakan router MikroTik. Setelah itu, dilakukan pengukuran parameter QoS yaitu, delay dan packet loss yang terjadi pada saat melakukan panggilan yang berlangsung selama satu jam. Dari hasil pengujian, diperoleh bahwa nilai MOS pada Google Hangouts lebih besar dibandingkan dengan Facebook Messenger, yaitu 4.0. Sedangkan pada Facebook Messenger hanya sebesar 3.6. Jika dikorelasikan ke tingkat kepuasan pengguna untuk mendapatkan nilai MOS, Google Hangouts dikategorikan "baik" dan Facebook Messenger dikategorikan "cukup baik".Kata kunci: MOS, LTE, VoIP, E-Model, GNS3 ABSTRACTThis study discusses the comparison of the quality of service of two VoIP applications, Facebook Messenger and Google Hangouts on LTE networks. The service quality of the two applications is reviewed using the Mean Opinion Score with an objective method namely, E-Model. MOS values from both applications are obtained by running simulations using GNS3 which can simulate network topology using a MikroTik router. After that, QoS parameters are measured, which are delay and packet loss during the call process which lasts one hour. From the test results, it was found that the MOS value on Google Hangouts was greater than Facebook Messenger, that is 4.0 while on Facebook Messenger only 3.6. If correlated with the level of user satisfaction to get MOS value, Google Hangouts is categorized as "good" and Facebook Messenger is categorized as "good enough".Keywords: MOS, LTE, VoIP, E-Model, GNS3 

scholarly journals Membangun Sistem Text-to-Audiovisual Bahasa Indonesia Berdasarkan Database Suara Berbasis Suku Kata Untuk Mendukung Pembelajaran Pelafalan Bahasa Indonesia

AITI ◽  
2018 ◽  
Vol 15 (1) ◽  
pp. 14-26
Author(s):  
Arifin Arifin ◽  
Surya Sumpeno ◽  
Mochamad Hariadi ◽  
Arry Maulana Syarif
Keyword(s):  
Speech Signal ◽  
Mean Opinion Score ◽  
Synchronization Process ◽  
Text Input ◽  
Input Text ◽  
Opinion Score ◽  
Speech Database ◽  
Lip Reading ◽  
Calculation Results ◽  
Bahasa Indonesia

This paper aims to develop a system Text-to-Audio Visual Indonesian to support learning of Indonesian pronunciation based on speech database syllable-based. This system can visualize the pronunciation of the sentences Indonesian synchronized with speech signals. We conduct several research stages, namely forming the Indonesian viseme models, creating the speech database syllable-based, converting the text into syllables dan synchronizing. The synchronization process is a compilation the viseme models and the speech signal based on input text. This system was evaluated by involving 30 respondents who rate the system based on “lip-reading”. Each respondent provides an assessment of the 10 Indonesian sentences about the level of compatibility between the visualization of syllable and speech spoken based on text input. The MOS methode (Mean Opinion Score) is used to calculate the average ratings of respondents. MOS calculation results is 4.24, It shows that the level of conformity visualization syllable pronunciation and spoken voice is good.

scholarly journals Development of Indonesian Text-to-Audiovisual Synthesis System Using Syllable Concatenation Approach to Support Indonesian Learning

2017 ◽  
Vol 12 (02) ◽  
pp. 166
Author(s):  
Arifin _ ◽  
Surya Sumpeno ◽  
Mochamad Hariadi ◽  
Arry Maulana Syarif
Keyword(s):  
Speech Signal ◽  
Mean Opinion Score ◽  
Synthesis System ◽  
Database Evaluation ◽  
Opinion Score ◽  
Speech Database ◽  
Calculation Results ◽  
Realistic Visualization

This study aims to develop of Indonesian Text-to-Audiovisual synthesis system using syllable concatenation approach to support Indonesian learning. This system can visualize the syllable pronunciation synchronized with the speech signal so that it can provide a realistic illustration of the articulator movement when each phoneme is pronounced. Syllable concatenation approach is used to realize a realistic visualization by assembling articulation and coarticulation in the form of syllables. In the development of the system, we have recorded speech database in the syllables form which refers to the patterns of syllables in Indonesian. The syllable concatenation approach is used to concatenate viseme of each phoneme, and to form the visualization of syllable pronunciations. It is synchronized with the corresponding speech from the speech database. Evaluation of this system is conducted based on a "lips-reading" of the 10 Indonesian sentences entered into the system. Ratings are based on the degree of correspondence between the syllable pronunciation and the speech produced. Assessment of all respondents is calculated using MOS (Mean Opinion Score). The calculation results show that the Indonesian text-to-audiovisual system has produced the pronunciation visualization more realistic and smoother.

Sistem Informasi Marketplace Penyewaan Barang Berbasis Web Dengan Framework Laravel

2021 ◽  
Vol 1 (2) ◽  
pp. 75-98
Author(s):  
Aji Nurcahyo Hidayat ◽  
Dadang Iskandar ◽  
Nofiyati Nofiyati
Keyword(s):  
Mean Opinion Score ◽  
Opinion Score

Pengguna internet di Indonesia terus mengalami peningkatan. Berdasarkan data dari Asosiasi Penyelenggara Jasa Internet Indonesia (APJII) tahun 2016, jumlah pengguna internet di Indonesia tumbuh sebesar 10,12%. Perkembangan yang semakin pesat ini di manfaatkan oleh berbagai pihak guna memaksimalkan fungsi dari kemajuan teknologi ini, yang salah satunya adalah dalam bidang jasa yaitu penyewaan atau rental barang. Banyaknya bisnis penyewaan barang yang muncul saat ini membuat penyewa barang seringkali lupa terkait informasi terkait produk yang ditawarkan. Kurangnya informasi atau promosi dari pemilik barang membuat calon penyewa sedikit kesulitan dan memerlukan usaha yang lebih untuk mendapatkan barang yang diinginkan, sehingga perlu adanya penyewaan berbasis website yang memuat informasi terkait produk yang ditawarkan. Penelitian ini bertujuan untuk membuat sistem marketplace yang memuduahkan bagi calon penyewa dalam menemukan barang yang diinginkan dan bagi pemilik barang untuk memudahkan memasarkan barangnya dan mengelola barang serta pesanannya. Cara kerja sistem ini, penyewa mencari barang yang diinginkan melalui sistem lalu memesannya. Pesanan tersebut kemudian dikirimkan ke pemilik barang oleh sistem setelah pembayaran untuk biaya sewa dikonfirmasi oleh admin dan pemilik barang dapat memberikan barangnya kepada penyewa sesuai data pesanannya. Sistem ini berbasis web dengan bahasa pemrograman PHP menggunakan framework laravel yang didukung basis data MySQL dan mengacu pada metode pengembangan waterfall pada proses pembuatannya. Tahap pengujian untuk sistem marketplace penyewaan barang dilakukan dengan metode pengujian blackbox testing dan Mean Opinion Score. Hasilnya menunjukan bahwa sitem berjalan sesuai dengan yang diharapkan dan mampu mebantu bagi calon penyewa dalam mencari informasi barang sewaan maupun bagi para pemilik barang dalam mempromosikan barangnya.

A Relative Fractal Dimension Spectrum for a Perceptual Complexity Measure

2011 ◽  
pp. 381-395
Author(s):  
W. Kinsner ◽  
R. Dansereau
Keyword(s):  
Fractal Dimension ◽  
Probability Distributions ◽  
Objective Measure ◽  
Mean Opinion Score ◽  
Perceptual Quality ◽  
Dimension Spectrum ◽  
Opinion Score ◽  
Single Scale ◽  
Scale Measure

This article presents a derivation of a new relative fractal dimension spectrum, DRq, to measure the dis-similarity between two finite probability distributions originating from various signals. This measure is an extension of the Kullback-Leibler (KL) distance and the Rényi fractal dimension spectrum, Dq. Like the KL distance, DRq determines the dissimilarity between two probability distibutions X and Y of the same size, but does it at different scales, while the scalar KL distance is a single-scale measure. Like the Rényi fractal dimension spectrum, the DRq is also a bounded vectorial measure obtained at different scales and for different moment orders, q. However, unlike the Dq, all the elements of the new DRq become zero when X and Y are the same. Experimental results show that this objective measure is consistent with the subjective mean-opinion-score (MOS) when evaluating the perceptual quality of images reconstructed after their compression. Thus, it could also be used in other areas of cognitive informatics.

Sign in / Sign up

Export Citation Format

Share Document