Informacja

Drogi użytkowniku, aplikacja do prawidłowego działania wymaga obsługi JavaScript. Proszę włącz obsługę JavaScript w Twojej przeglądarce.

English (EN)·Polski (PL)·Yкраїнський (UK)
Przejdź do strony domowej biblioteki Centralna Biblioteka Wojskowa Link otwiera się w nowym oknie Logo biblioteki Prolib Integro - strona głównaCentralna Biblioteka Wojskowa

Wyszukujesz frazę "packet" wg kryterium: Temat

  Lista filtrów
Wyrównaj
Wyświetlanie 1-15 z 64
Tytuł:
Time - frequency method and artificial neural network classifier for induction motor drive system defects classification
Autorzy:
Behim, Meriem
Merabet, Leila
Saad, Salah
Powiązania:
https://bibliotekanauki.pl/articles/31341644.pdf
Data publikacji:
2024
Wydawca:
Polska Akademia Nauk. Polskie Towarzystwo Diagnostyki Technicznej PAN
Tematy:
energy
L-kurtosis
wavelet packet decomposition
multilayer perceptron neural network
induction motor defects
vibratory signals
Opis:
In this paper, by introducing two statistical parameters, energy and L-kurtosis, a new fault diagnostic system combining Wavelet Packet Decomposition and Multilayer Perceptron Neural Network is designed to improve efficiency and precision of induction motor defects diagnosis. This method is applied to vibratory signals of asynchronous motor running at two different rotational speeds (1500 rpm and 2000 rpm) at a sampling frequency of 8 KHz to detect three main types of defects: bearing faults, load imbalance and misalignment. These speeds are considered as the usual medium running speeds of induction motor. According to the results, the high performance and accuracy of this new faults diagnostic system is proved and confirmed, thus it can be used in the detection of other machines defects.
Źródło:
Diagnostyka; 2024, 25, 1; art. no. 2024110
1641-6414
2449-5220
Pojawia się w:
Diagnostyka
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Analysis of Latency-Aware Network Slicing in 5G Packet xHaul Networks
Autorzy:
Klinkowski, Mirosław
Powiązania:
https://bibliotekanauki.pl/articles/27311921.pdf
Data publikacji:
2023
Wydawca:
Polska Akademia Nauk. Czasopisma i Monografie PAN
Tematy:
5G
radio access networks
packet-switched xHaul
latency-sensitive network
network slicing
traffic prioritization
network optimization
Opis:
Packet-switched xHaul networks are a scalable solution enabling convergent transport of diverse types of radio data flows, such as fronthaul / midhaul / backhaul (FH / MH / BH) flows, between remote sites and a central site (hub) in 5G radio access networks (RANs). Such networks can be realized using the cost-efficient Ethernet technology, which enhanced with time-sensitive networking (TSN) features allows for prioritized transmission of latency-sensitive fronthaul flows. Provisioning of multiple types of 5G services of different service requirements in a shared network, commonly referred to as network slicing, requires adequate handling of transported data flows in order to satisfy particular service / slice requirements. In this work, we investigate two traffic prioritization policies, namely, flowaware (FA) and latency-aware (LA), in a packet-switched xHaul network supporting slices of different latency requirements. We evaluate the effectiveness of the policies in a networkplanning case study, where virtualized radio processing resources allocated at the processing pool (PP) facilities, for two slices related to enhanced mobile broadband (eMBB) and ultra-reliable low latency communications (URLLC) services, are subject to optimization. Using numerical experiments, we analyze PP cost savings from applying the LA policy (vs. FA) in various network scenarios. The savings in active PPs reach up to 40% − 60% in ring scenarios and 30% in a mesh network, whereas the gains in overall PP cost are up to 20% for the cost values assumed in the analysis.
Źródło:
International Journal of Electronics and Telecommunications; 2023, 69, 2; 335--340
2300-1933
Pojawia się w:
International Journal of Electronics and Telecommunications
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Sleep Snoring Sound Recognition Based on Wavelet Packet Transform
Autorzy:
Ding, Li
Peng, Jianxin
Zhang, Xiaowen
Song, Lijuan
Powiązania:
https://bibliotekanauki.pl/articles/31339924.pdf
Data publikacji:
2023
Wydawca:
Polska Akademia Nauk. Czasopisma i Monografie PAN
Tematy:
snoring recognition
wavelet packet transform
feature selection
machine learning
Opis:
Snoring is a typical and intuitive symptom of the obstructive sleep apnea hypopnea syndrome (OSAHS), which is a kind of sleep-related respiratory disorder having adverse effects on people’s lives. Detecting snoring sounds from the whole night recorded sounds is the first but the most important step for the snoring analysis of OSAHS. An automatic snoring detection system based on the wavelet packet transform (WPT) with an eXtreme Gradient Boosting (XGBoost) classifier is proposed in the paper, which recognizes snoring sounds from the enhanced episodes by the generalization subspace noise reduction algorithm. The feature selection technology based on correlation analysis is applied to select the most discriminative WPT features. The selected features yield a high sensitivity of 97.27% and a precision of 96.48% on the test set. The recognition performance demonstrates that WPT is effective in the analysis of snoring and non-snoring sounds, and the difference is exhibited much more comprehensively by sub-bands with smaller frequency ranges. The distribution of snoring sound is mainly on the middle and low frequency parts, there is also evident difference between snoring and non-snoring sounds on the high frequency part.
Źródło:
Archives of Acoustics; 2023, 48, 1; 3-12
0137-5075
Pojawia się w:
Archives of Acoustics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Token Bucket Algorithm with Modernization Techniques to avoid Congestion in DEC Protocol of WSN
Autorzy:
Mohammad, Habibulla
Krishna, K. Phani Rama
Gangadhar, Ch
Mohammed, Riazuddin
Powiązania:
https://bibliotekanauki.pl/articles/27311894.pdf
Data publikacji:
2023
Wydawca:
Polska Akademia Nauk. Czasopisma i Monografie PAN
Tematy:
Packet size
Token bucket
Queue
Base station
Residual energy
congestion
Opis:
A wireless sensor system is an essential aspect in many fields. It consists of a great deal of sensor nodes. These sensor networks carry out a number of tasks, including interaction, distribution, recognition, and power supply. Data is transmitted from source to destination and plays an important role. Congestion may occur during data transmission from one node to another and also at cluster head locations. Congestion will arise as a result of either traffic division or resource allocation. Energy will be wasted due to traffic division congestion, which causes packet loss and retransmission of removed packets. As a result, it must be simplified; hence there are a few Wireless sensor networks with various protocols that will handle Congestion Control. The Deterministic Energy Efficient Clustering (DEC) protocol, which is fully based on residual energy and the token bucket method, is being investigated as a way to increase the energy efficiency. In the event of congestion, our proposal provides a way to cope with it and solves it using this method to improve lifespan of the sensor networks. Experiments in simulation show that the proposed strategy can significantly enhance lifetime, energy, throughput, and packet loss.
Źródło:
International Journal of Electronics and Telecommunications; 2023, 69, 3; 507--513
2300-1933
Pojawia się w:
International Journal of Electronics and Telecommunications
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A Rattle Signal Denoising and Enhancing Method Based on Wavelet Packet Decomposition and Mathematical Morphology Filter for Vehicle
Autorzy:
Liang, Linyuan
Chen, Shuming
Li, Peiran
Powiązania:
https://bibliotekanauki.pl/articles/2141688.pdf
Data publikacji:
2022
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
rattle signals
wavelet packet decomposition
mathematical morphology filter
critical frequency band
information entropy
Opis:
Buzz, squeak and rattle (BSR) noise has become apparent in vehicles due to the significant reductions in engine noise and road noise. The BSR often occurs in driving condition with many interference signals. Thus, the automatic BSR detection remains a challenge for vehicle engineers. In this paper, a rattle signal denoising and enhancing method is proposed to extract the rattle components from in-vehicle background noise. The proposed method combines the advantages of wavelet packet decomposition and mathematical morphology filter. The critical frequency band and the information entropy are introduced to improve the wavelet packet threshold denoising method. A rattle component enhancing method based on multi-scale compound morphological filter is proposed, and the kurtosis values are introduced to determine the best parameters of the filter. To examine the feasibility of the proposed algorithm, synthetic brake caliper rattle signals with various SNR ratios are prepared to verify the algorithm. In the validation analysis, the proposed method can well remove the disturbance background noise in the signal and extract the rattle components with well SNR ratios. It is believed that the algorithm discussed in this paper can be further applied to facilitate the detection of the vehicle rattle noise in industry.
Źródło:
Archives of Acoustics; 2022, 47, 1; 43-55
0137-5075
Pojawia się w:
Archives of Acoustics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Light Weight Clustered Trust Sensing Mechanism for Internet of Things Network
Autorzy:
Rajendra Prasad, M.
Krishna Reddy, D.
Powiązania:
https://bibliotekanauki.pl/articles/2055236.pdf
Data publikacji:
2022
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
internet of things
trust sensing
clustering
mobility
packet forwarding factor
malicious detection rate
packet delivery ratio
Opis:
Internet of Things (IoT) is the new research paradigm which has gained a great significance due to its widespread applicability in diverse fields. Due to the open nature of communication and control, the IoT network is more susceptible to several security threats. Hence the IoT network requires a trust aware mechanism which can identify and isolate the malicious nodes. Trust Sensing has been playing a significant role in dealing with security issue in IoT. A novel a Light Weight Clustered Trust Sensing (LWCTS) model is developed which ensures a secured and qualitative data transmission in the IoT network. Simulation experiments are conducted over the proposed model and the performance is compared with existing models. The obtained results prove the effectiveness when compared with existing approaches.
Źródło:
International Journal of Electronics and Telecommunications; 2022, 68, 1; 5--12
2300-1933
Pojawia się w:
International Journal of Electronics and Telecommunications
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Analysis of the Discrete-time Multi-queue System with a Cycle-based Scheduler
Autorzy:
Burakowski, Wojciech
Sosnowski, Maciej
Powiązania:
https://bibliotekanauki.pl/articles/1839463.pdf
Data publikacji:
2021
Wydawca:
Instytut Łączności - Państwowy Instytut Badawczy
Tematy:
discrete-time queueing system with vacations
system state distribution
packet sojourn time distribution
virtualized system
Opis:
This paper presents an analysis of a discrete-time multi-queue system handling a number of packet streams. The analysis focuses on calculating system state distribution and packet sojourn time distribution. The method relied upon for determining system state distribution is based on creating a number of equations that are solved numerically. Next, based on the distribution calculated in such a manner, we derive relations for packet sojourn time distribution. The models studied may be useful for instance in a system supporting a number of virtual links (each of a constant bitrate) that share a common physical link. Isolation of performance of those virtual links needs to be assured. Finally, we present some exemplary numerical results showing the usefulness of the proposed analysis for supporting the system dimensioning process.
Źródło:
Journal of Telecommunications and Information Technology; 2021, 2; 68-76
1509-4553
1899-8852
Pojawia się w:
Journal of Telecommunications and Information Technology
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Analysis of The Effectiveness of Online Electronic Learning System Using Data Traffic Network Performance Management to Succeed Merdeka Learning : Merdeka Campus During the Covid-19 Pandemic
Autorzy:
Budiyanto, Setiyo
Silalahi, Lukman Medriavin
Silaban, Freddy Artadima
Sitorus, Henry Binsar Hamonangan
Rochendi, Agus Dendi
Ismail, Mochamad Furqon
Powiązania:
https://bibliotekanauki.pl/articles/2055225.pdf
Data publikacji:
2021
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
delay
throughput
packet loss
education
Opis:
The problems in the Covid-19 pandemic have a major influence on the field of education with the use of technology to support the teaching and learning process to facilitate students who do home learning activities. The proposed concept of freedom of learning is a more comprehensive concept such as portfolio and assignments such as group assignments, writings, and so on that are done in full online by adding additional features such as Teaching and Learning Activities and Assessment through information technology media. (E-Learning / Learning Management System). The method proposed in this research is the Peer Connection Queue (PCQ) method on mikrotik operating systems. PCQ method is a program to manage network traffic in Quality of Services (QoS). Bandwidth management methods. The hypothesis formulated is to create bandwidth management with PCQ so that bandwidth sharing is automatically and evenly distributed to multi clients. Therefore, in this research finally formulated into the goal of E-Learning effectiveness analysis using bandwidth management analysis method, which will be measured and analyzed in this research is throughput, delay, jitter, and packet loss. So that the final result of this research obtained the feasibility of the teaching and learning process that is carried out effectively.
Źródło:
International Journal of Electronics and Telecommunications; 2021, 67, 4; 595--601
2300-1933
Pojawia się w:
International Journal of Electronics and Telecommunications
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
City Backbone Network Traffic Forecasting
Autorzy:
Serikov, Tansaule
Zhetpisbayeva, Ainur
Аkhmediyarova, Аinur
Mirzakulova, Sharafat
Aigerim, Kismanova
Tolegenova, Aray
Wójcik, Waldemar
Powiązania:
https://bibliotekanauki.pl/articles/1844529.pdf
Data publikacji:
2021
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
time series
packet intensity
Dickey-Fuller test
Kwiatkowski-Phillips-Perron-Shin-Schmitt test
forecasting
integrated moving average autoregression model
Opis:
The work considers a one-dimensional time series protocol packet intensity, measured on the city backbone network. The intensity of the series is uneven. Scattering diagrams are constructed. The Dickie Fuller test and Kwiatkowski-Phillips Perron-Shin-Schmitt test were applied to determine the initial series to the class of stationary or non-stationary series. Both tests confirmed the involvement of the original series in the class of differential stationary. Based on the Dickie Fuller test and Private autocorrelation function graphs, the Integrated Moving Average Autoregression Model model is created. The results of forecasting network traffic showed the adequacy of the selected model.
Źródło:
International Journal of Electronics and Telecommunications; 2021, 67, 3; 319-324
2300-1933
Pojawia się w:
International Journal of Electronics and Telecommunications
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Phonetic Segmentation using a Wavelet-based Speech Cepstral Features and Sparse Representation Classifier
Autorzy:
Al-Hassani, Ihsan
Al-Dakkak, Oumayma
Assami, Abdlnaser
Powiązania:
https://bibliotekanauki.pl/articles/2058484.pdf
Data publikacji:
2021
Wydawca:
Instytut Łączności - Państwowy Instytut Badawczy
Tematy:
Arabic speech corpus
ASR
F1-score
phonetic segmentation
sparse representation classifier
TTS
wavelet packet
Opis:
Speech segmentation is the process of dividing speech signal into distinct acoustic blocks that could be words, syllables or phonemes. Phonetic segmentation is about finding the exact boundaries for the different phonemes that composes a specific speech signal. This problem is crucial for many applications, i.e. automatic speech recognition (ASR). In this paper we propose a new model-based text independent phonetic segmentation method based on wavelet packet speech parametrization features and using the sparse representation classifier (SRC). Experiments were performed on two datasets, the first is an English one derived from TIMIT corpus, while the second is an Arabic one derived from the Arabic speech corpus. Results showed that the proposed wavelet packet decomposition features outperform the MFCC features in speech segmentation task, in terms of both F1-score and R-measure on both datasets. Results also indicate that the SRC gives higher hit rate than the famous k-Nearest Neighbors (k-NN) classifier on TIMIT dataset.
Źródło:
Journal of Telecommunications and Information Technology; 2021, 4; 12--22
1509-4553
1899-8852
Pojawia się w:
Journal of Telecommunications and Information Technology
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Pupils’ Opinions on Digital Systems Education Enriched by DCBLP Discourse
Autorzy:
Hapl, Lukáš
Kostolányová, Kateřina
Habiballa, Hashim
Powiązania:
https://bibliotekanauki.pl/articles/1964300.pdf
Data publikacji:
2021-09-30
Wydawca:
Wydawnictwo Adam Marszałek
Tematy:
DCBLP
digital systems
e-learning
Packet Tracer
students’ opinions
Opis:
The article presents knowledge about the modified e-learning on-line synchronous teaching of digital systems, which took place in the period of widespread closure of schools during almost the entire school year 2020/2021 at a secondary school with an IT focus. The importance of teaching digital systems in computer science and the integration of teaching into available lessons is briefly clarified. Furthermore, the content of teaching is presented, including its modification by elements of programming by DCBLP discourse and links to existing knowledge about this use from previous years. The subject of research interest will be the specific effects of changes on students’ opinions regarding the content of the subject. For this purpose, a qualitative investigation based on the design of the grounded theory will be used. The work brings partial knowledge that can serve as additional material for the determination of other research questions, hypotheses and identification of potential problems in teaching. The results show the pupils’ interest in the digital systems enriched by the programming discourse reveals the possible perception of a long time distance learning in this area.
Źródło:
The New Educational Review; 2021, 65; 200-210
1732-6729
Pojawia się w:
The New Educational Review
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Speech emotion recognition using wavelet packet reconstruction with attention-based deep recurrent neutral networks
Autorzy:
Meng, Hao
Yan, Tianhao
Wei, Hongwei
Ji, Xun
Powiązania:
https://bibliotekanauki.pl/articles/2173587.pdf
Data publikacji:
2021
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
speech emotion recognition
voice activity detection
wavelet packet reconstruction
feature extraction
LSTM networks
attention mechanism
rozpoznawanie emocji mowy
wykrywanie aktywności głosowej
rekonstrukcja pakietu falkowego
wyodrębnianie cech
mechanizm uwagi
sieć LSTM
Opis:
Speech emotion recognition (SER) is a complicated and challenging task in the human-computer interaction because it is difficult to find the best feature set to discriminate the emotional state entirely. We always used the FFT to handle the raw signal in the process of extracting the low-level description features, such as short-time energy, fundamental frequency, formant, MFCC (mel frequency cepstral coefficient) and so on. However, these features are built on the domain of frequency and ignore the information from temporal domain. In this paper, we propose a novel framework that utilizes multi-layers wavelet sequence set from wavelet packet reconstruction (WPR) and conventional feature set to constitute mixed feature set for achieving the emotional recognition with recurrent neural networks (RNN) based on the attention mechanism. In addition, the silent frames have a disadvantageous effect on SER, so we adopt voice activity detection of autocorrelation function to eliminate the emotional irrelevant frames. We show that the application of proposed algorithm significantly outperforms traditional features set in the prediction of spontaneous emotional states on the IEMOCAP corpus and EMODB database respectively, and we achieve better classification for both speaker-independent and speaker-dependent experiment. It is noteworthy that we acquire 62.52% and 77.57% accuracy results with speaker-independent (SI) performance, 66.90% and 82.26% accuracy results with speaker-dependent (SD) experiment in final.
Źródło:
Bulletin of the Polish Academy of Sciences. Technical Sciences; 2021, 69, 1; art. no. e136300
0239-7528
Pojawia się w:
Bulletin of the Polish Academy of Sciences. Technical Sciences
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Speech emotion recognition using wavelet packet reconstruction with attention-based deep recurrent neutral networks
Autorzy:
Meng, Hao
Yan, Tianhao
Wei, Hongwei
Ji, Xun
Powiązania:
https://bibliotekanauki.pl/articles/2090711.pdf
Data publikacji:
2021
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
speech emotion recognition
voice activity detection
wavelet packet reconstruction
feature extraction
LSTM networks
attention mechanism
rozpoznawanie emocji mowy
wykrywanie aktywności głosowej
rekonstrukcja pakietu falkowego
wyodrębnianie cech
mechanizm uwagi
sieć LSTM
Opis:
Speech emotion recognition (SER) is a complicated and challenging task in the human-computer interaction because it is difficult to find the best feature set to discriminate the emotional state entirely. We always used the FFT to handle the raw signal in the process of extracting the low-level description features, such as short-time energy, fundamental frequency, formant, MFCC (mel frequency cepstral coefficient) and so on. However, these features are built on the domain of frequency and ignore the information from temporal domain. In this paper, we propose a novel framework that utilizes multi-layers wavelet sequence set from wavelet packet reconstruction (WPR) and conventional feature set to constitute mixed feature set for achieving the emotional recognition with recurrent neural networks (RNN) based on the attention mechanism. In addition, the silent frames have a disadvantageous effect on SER, so we adopt voice activity detection of autocorrelation function to eliminate the emotional irrelevant frames. We show that the application of proposed algorithm significantly outperforms traditional features set in the prediction of spontaneous emotional states on the IEMOCAP corpus and EMODB database respectively, and we achieve better classification for both speaker-independent and speaker-dependent experiment. It is noteworthy that we acquire 62.52% and 77.57% accuracy results with speaker-independent (SI) performance, 66.90% and 82.26% accuracy results with speaker-dependent (SD) experiment in final.
Źródło:
Bulletin of the Polish Academy of Sciences. Technical Sciences; 2021, 69, 1; e136300, 1--12
0239-7528
Pojawia się w:
Bulletin of the Polish Academy of Sciences. Technical Sciences
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A Study on Packet Scheduling Algorithms for Healthcare Contents over Fifth Generation (5G) Mobile Cellular Network
Autorzy:
Ramli, Huda Adibah Mohd
Powiązania:
https://bibliotekanauki.pl/articles/1844466.pdf
Data publikacji:
2020
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
packet scheduling
5G
flexible frame structure
transmission reliability
scalable TTI
Opis:
This paper models the downlink Fifth Generation (5G) network that supports a flexible frame structure and a shorter Round-Trip Time (RTT) for Hybrid Automatic Repeat Request (HARQ). Moreover, the design of the renowned Time Division Multiple Access (TDMA) packet scheduling algorithms is revised to allow these algorithms to support packet scheduling in the downlink 5G. Simulation results demonstrate that the Proportional Fair provides a comparable performance to the delay–aware Maximum-Largest Weighted Delay First for simultaneously providing the desired transmission reliability of the Guaranteed Bit Rate (GBR) and Non-Guaranteed Bit Rate (Non - GBR) healthcare contents whilst maximizing the downlink 5G performance.
Źródło:
International Journal of Electronics and Telecommunications; 2020, 66, 4; 729-735
2300-1933
Pojawia się w:
International Journal of Electronics and Telecommunications
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Speech Enhancement Based on Discrete Wavelet Packet Transform and Itakura-Saito Nonnegative Matrix Factorisation
Autorzy:
Liu, Houguang
Wang, Wenbo
Xue, Lin
Yang, Jianhua
Wang, Zhihua
Hua, Chunli
Powiązania:
https://bibliotekanauki.pl/articles/1448505.pdf
Data publikacji:
2020
Wydawca:
Polska Akademia Nauk. Czasopisma i Monografie PAN
Tematy:
speech enhancement
discrete wavelet packet transform
nonnegative matrix factorisation
Itakura-Saito divergence
Opis:
Nonnegative matrix factorization (NMF) is one of the most popular machine learning tools for speech enhancement (SE). However, there are two problems reducing the performance of the traditional NMF-based SE algorithms. One is related to the overlap-and-add operation used in the short time Fourier transform (STFT) based signal reconstruction, and the other is the Euclidean distance used commonly as an objective function; these methods can cause distortion in the SE process. In order to get over these shortcomings, we propose a novel SE joint framework which combines the discrete wavelet packet transform (DWPT) and the Itakura-Saito nonnegative matrix factorisation (ISNMF). In this approach, the speech signal was first split into a series of subband signals using the DWPT. Then, the ISNMF was used to enhance the speech for each subband signal. Finally, the inverse DWPT (IDWT) was utilised to reconstruct these enhanced speech subband signals. The experimental results show that the proposed joint framework effectively enhances the performance of speech enhancement and performs better in the unseen noise case compared to the traditional NMF methods.
Źródło:
Archives of Acoustics; 2020, 45, 4; 565-572
0137-5075
Pojawia się w:
Archives of Acoustics
Dostawca treści:
Biblioteka Nauki
Artykuł
Wyświetlanie 1-15 z 64

Ta witryna wykorzystuje pliki cookies do przechowywania informacji na Twoim komputerze. Pliki cookies stosujemy w celu świadczenia usług na najwyższym poziomie, w tym w sposób dostosowany do indywidualnych potrzeb. Korzystanie z witryny bez zmiany ustawień dotyczących cookies oznacza, że będą one zamieszczane w Twoim komputerze. W każdym momencie możesz dokonać zmiany ustawień dotyczących cookies