Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 12

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  speech quality
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
EN
In October 2018, local digital radio was launched to cover the agglomeration of Wroclaw. The implementation of this undertaking required many tests, including qualitative ones, that refer to both music and speech. This paper presents the results of subjective tests based on the evaluation of speech quality of signals recorded at various points in Wroclaw. Measurements were carried out in accordance with the recommendations of the International Telecommunication Union as well as in ordinary acoustic conditions in listeners’ flats. The rating was made for male and female voices. The most important conclusion is that for speech signal assessment in meaning of the quality the test conditions do not influence the obtained results. The other fact confirmed in the experiment was that the receiving place of DAB+ signal in the Single-Frequency Network also does not affect the perceived voice quality.
2
Content available remote Computational intelligence for speech enhancement using deep neural network
EN
In real time, the speech signal received contains noise produced in the background andreverberations. These disturbances reduce the quality of speech; therefore, it is importantto eliminate the noise and increase the intelligibility and quality of speech signal. Speechenhancement is the primary task in any real-time application that handles speech signals.In the proposed method, the most effective and challenging noise, i.e., babble noise, isremoved, and the clean speech is recovered. The enhancement of the corrupted speechsignal is done by applying a deep neural network-based denoising algorithm in which theideal ratio mask is used to mask the noisy speech and separate the clean speech signal.In the proposed system, the speech signal corrupted by noise is enhanced. Evaluation ofenhanced speech signal by performance metrics such as short time objective intelligibilityand signal to noise ratio of the denoised speech show that the speech intelligibility andspeech quality are improved by the proposed method.
EN
The article presents the results of research regarding the impact of the degree of distortion and noise of the logatom (nonsense word) on the listener's reaction time. The study aimed to determine the maximum reaction time of listeners, which will allow determining the time after which the logatom will be exposed in the speech quality assessment method with an alternative choice. The research was carried out with the participation of a group of ten students. A strong relationship between the results obtained and the concentration of the listeners was found, as well as the effect of fatigue, training, and the gender of the listener. The obtained results indicate that in the method with an alternative choice before the logatom emission should appear 1.1 s initial sequence, which will eliminate the situation when the listeners did not recognize the initial phoneme transmitted from the logatom.
PL
W październiku 2018 roku została uruchomiona lokalna radiofonia cyfrowa pokrywająca swoim zasięgiem aglomerację Wrocławia. Realizacja tego przedsięwzięcia wymagała wykonania wielu testów, w tym również jakościowych odnoszących się zarówno do muzyki jak i mowy. W niniejszym artykule przedstawiono wyniki testów jakościowych opartych na ocenie jakości mowy sygnałów nagranych w różnych punktach Wrocławia. Pomiary wykonano zgodnie z zaleceniami International Telecommunication Union. Ocena została wykonana dla głosu męskiego i żeńskiego.
EN
In October 2018, local digital radio was launched to cover the agglomeration of Wrocław. The implementation of this undertaking required many tests, including qualitative ones, referring to both music and speech. This article presents the results of qualitative tests based on evaluation of speech quality of signals recorded at various points in Wrocław. The measurements were carried out in accordance with the recommendations of the International Telecommunication Union. The rating was made for male and female voice.
EN
Paper presents the results of quality assessment of speech and music signals transmitted via DAB+ system with the use of Single Frequency Network (SFN). The musical signals were evaluated in overall quality domain. The subjective research was provided with the use of Absolute Category Rating procedure according to the ITU recommendation and the results have been presented as the MOS values for various bit rates. The speech signals were additionally examined with PESQ method. The results have shown that the assumed quality of 4 MOS, for this kind of broadcasting could be achieved at 48 kb/s for speech and 64 kb/s for music. This fact was confirmed by both: subjective and objective research. The comparison between the results obtained for SFN broadcasting with three emitters with single-emitter broadcast was presented.
PL
Proces cyfryzacji radia jest nowym rozdziałem w historii radiofonii. Wiele rekomendacji i badań naukowych wskazuje na standard DAB+ (Digital Audio Broadcasting plus), który w niedalekiej przyszłości ma zastąpić analogową radiofonię FM. Ten system cyfrowy wprowadza wiele zmian, oferując przy tym lepszą jakość dźwięku oraz szereg usług dodatkowych. W pracy postanowiono zbadać minimalną wymaganą przepływność bitową potrzebną do transmisji głosowych komunikatów drogowych w ramach radiofonii cyfrowej DAB+.
EN
The process of digitizing radio marks a new chapter in the history of broadcasting. Numerous recommendations and scientific publications point out to DAB+ (Digital Audio Broadcasting plus), as the standard that will replace traditional analog FM radio in the nearest future. This digital system implies changes, offering higher sound quality, as well as a set of additional services. In this work we present a study concerning minimal required bitrate necessary for transmitting voice traffic messages in the DAB+ broadcasting system.
PL
Jedną z wielu usług świadczonych przez operatorów telefonii mobilnej jest usługa głosowa. Jej funkcjonalność w dużej mierze zależy od jakości mowy. W artykule przedstawiono ocenę subiektywną i obiektywną usługi głosowej świadczonej przez czterech, największych operatorów działających w Polsce. Pomiary wykonano w centrum Wrocławia w okresie jednego tygodnia w odstępach dwugodzinnych. Przedstawiono ocenę świadczonej usługi w układzie zarówno dziennym jak i godzinowym.
EN
One of the many services provided by mobile telephony operators is a voice service. Its functionality depends to a large extent on the quality of speech. This article presents a subjective and objective evaluation of the voice service provided by four major operators working in Poland. Measurements were made in the center of Wroclaw within one week at two-hour intervals. The assessment of the service provided is presented both on a daily and hourly basis.
EN
Speech enhancement is fundamental for various real time speech applications and it is a challenging task in the case of a single channel because practically only one data channel is available. We have proposed a supervised single channel speech enhancement algorithm in this paper based on a deep neural network (DNN) and less aggressive Wiener filtering as additional DNN layer. During the training stage the network learns and predicts the magnitude spectrums of the clean and noise signals from input noisy speech acoustic features. Relative spectral transform-perceptual linear prediction (RASTA-PLP) is used in the proposed method to extract the acoustic features at the frame level. Autoregressive moving average (ARMA) filter is applied to smooth the temporal curves of extracted features. The trained network predicts the coefficients to construct a ratio mask based on mean square error (MSE) objective cost function. The less aggressive Wiener filter is placed as an additional layer on the top of a DNN to produce an enhanced magnitude spectrum. Finally, the noisy speech phase is used to reconstruct the enhanced speech. The experimental results demonstrate that the proposed DNN framework with less aggressive Wiener filtering outperforms the competing speech enhancement methods in terms of the speech quality and intelligibility.
EN
A method of evaluation of speech transmission quality, called "modified intelligibility test with forced choice" (MIT-FC), is presented. This method provides a~fully automated measurement of speech intelligibility (the listener's task is to select on the computer monitor which of the alternative utterances presented visually to him was spoken). The MIT-FC method was implemented in a stationary version for measurements of telecommunication systems and chains and in a portable version for the measurements of auditoria and mobile communication systems. The results of application of the MIT-FC method in telecommunications have been presented and the results obtained have been compared with those of traditional intelligibility tests.
EN
An objective measure of the quality of speech communication channels was introduced and described by Steeneken-Houtgast. By calculating the Speech Transmission Index (STI), this method provides an estimate of logatom intelligibility for a variety of communication distortions. Using the logatom test for speech intelligibility, it was shown that the STI method is a valid method for the assessment of the quality of the speech transmitted over communications channels intended for use with the Polish language. New STI curves were generated for the Polish speech intelligibility.
PL
Pomiar jakości głosu w telefonii nie jest nowym problemem. Utrata pakietów (packet loss) oraz wariancja opóźnienia (jitter), występujące w sieciach wykorzystujących protokół IP, wprowadzają dodatkowe zniekształcenia wpływające na jakość transmitowanej mowy. W artykule opisano wyniki badań wpływu języka na wartość uśrednionej opinii słuchaczy MOS (Mean Opinion Score) przy różnym poziomie utraty pakietów. Przedstawiono wyznaczone doświadczalnie wartości współczynnika odporności na utratę pakietów Bpl (Packet Loss Robustness Factor) dla różnych języków.
EN
Measuring voice quality for telephony is not a new problem. Packet loss and jitter, which occur in packet switched networks such as Internet, introduce distortions influence on speech quality. In this paper we show how languages affect the Mean Opinion Score (MOS) at different packet loss rate. Finally, we show correct values of Packet Loss Robustness Factor Bpl for different languages.
PL
Przedstawiono parametry toru transmisyjnego wpływające na jakość mowy transmitowanej w sieciach komórkowych. Omówiono wyniki badania wpływu tych parametrów na jakość sygnału mowy. Opisano metodę VoQ oraz uzyskane wyniki oceny jakości mowy z parametrów przekazywanych podczas transmisji.
EN
This paper presents subjective and objective measurement methods of speech quality. Selected transmission parameters was described and showed their influence on speech quality. This paper presents description of VoQ method. Finally, it was make a choice of right methods in order to speech quality assessment in cellular network.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.