Wyniki wyszukiwania - BazTech

1

Singing voice analysis on the basis of acoustic parameters

Bednarz Natalia, Madej Zdzisław

Vibrations in Physical Systems

|

2023

|

Vol. 34, nr 2

art. no. 2023211

EN

Voice plays a fundamental role in human relations. In addition to its communicative function in everyday life, the voice also acts as an instrument or a working tool for singers, teachers or actors. It is said that singing is an extension of speech, but performing it correctly is a complex task that requires hard work and training. This paper draws attention to the problem of insufficient training in voice emission and voice control of singers in amateur choirs, which can cause strain and disorders of the phonatory system. Tool that can assess the quality of a person's singing on the basis of acoustic parameters may prove useful. In order to determine parameters that could help evaluate the correctness of singing, a study was conducted on a group of 10 choir members and one professional singer. The study consisted of recording the singers' voice during singing and speech. The subjects performed simple vocal exercises consisting mainly in upward and downward sound modulation. In this study, portions of the recordings were analysed to determine parameters like Maximal Phonation Time (MPT), Singing Power Ratio (SPR) or signal integral. The values of obtained parameters for the choristers were compared with the results of the professional singer, which allowed to select those parameters that may be helpful in the evaluation of the singing voice. The parameters for which the connection between their value and singing correctness has been shown create a vector of features that can be used to assess the correctness of classical singing. The paper also describes further research plan.

2

Intonation accuracy and pitch stability during crescendo as the voice quality and singer’s experience indicator among choral singers

Gawlik Mateusz, Wszołek Wiesław

Vibrations in Physical Systems

|

2019

|

Vol. 30, nr 1

art. no. 2019138

EN

The ability to correctly reproduce notes by the voice is one of the essential features of the singing task and called intonation. In combination with other parameters like timbre, formants, and sound attack, it affects the reception of listening impressions. In this paper, we present results of the examination concerning the automatic evaluation of intonation among the nonsingers, untrained and trained choral singers. We performed both pitch error during vocalization and pitch stability in crescendo task analysis among studied groups. We used Zero Band Filtering method to determine fundamental frequency from the singing signal. We noticed significant differences between singers with different skills and experience, and the possibility to classify the level of advancement of the singer by using intonation characteristic.

3

Computer analysis of the noise component in the singing voice for assessing the quality of singing

Półrolniczak E., Kramarczyk M.

Przegląd Elektrotechniczny

|

2015

|

R. 91, nr 2

79-83

EN

The article focuses on the analysis of a noise in singing voices using samples obtained from choral singers. Analysis of the singing voice quality is a complex task. There are various points of view and methods of analysis used to solve that problem. Musicians consider the voice of singers from the point of view of voice emission. Doctors analyzing the voice of a singer trying to determine his medical parameters. To analyze the quality of singing voice the equipment and tools characteristic for clinical practice can be used. In the analysis of the signals mentioned in the article some methods for the voice analysis have been adopted. The quality parameters of the singing voice were calculated on the basis of recorded samples. This article presents the results of research at the frontier of computer signal analysis and medicine. To achieve the goal in the study a method for the analysis of noise Noise Parameter based on GNE (Glottal-to-Noise Excitation Ratio) was used.

PL

Niniejszy artykuł skupia się na analizie szumu w głosie śpiewaczym. Analiza jakości głosu śpiewaczego jest złożonym zadaniem. W praktyce istnieją różne podejścia do analizy zagadnienia szumu w głosie. Muzycy patrzą na głos śpiewaczy z perspektywy emisji głosu. Lekarze analizując głos śpiewaka próbują ustalić jego parametry medyczne. Stosowane są przy tym narzędzia wykorzystywane do analiz medycznych. W przedstawionej w tym artykule analizie parametry jakościowe głosu śpiewaczego obliczono dla próbek dźwiękowych pozyskanych od śpiewaków chóralnych. Przedstawiono tutaj wyniki badań z pogranicza komputerowej analizy sygnału i medycyny. Aby osiągnąć założony cel wykorzystano metody analizy parametrów szumu na podstawie współczynnika GNE (Glottal-to-Noise Excitation Ratio).

4

Computer aided determination of singing voice sonority

Półrolniczak E.

Elektronika : konstrukcje, technologie, zastosowania

|

2015

|

Vol. 56, nr 4

20-22

EN

The article touches upon the interdisciplinary subject of computer analysis of sonority feature in singing. The aim is to find the parameters that reflect the impression of sonority in timbre. The article attempts to define more precisely what is sonority in singing and what is sonorous voice. For the evaluation of the sonority of singing voice ten signal parameters were selected, calculated and compared with opinions of 5 experts assessing sonority feature in the recorded singing. Due to the differences in the vocal scales of women and men, singers were analysed in separated groups.

PL

Niniejszy artykuł dotyka interdyscyplinarnego zagadnienia jakim jest analiza cechy dźwięczności w śpiewie. Celem opracowania jest znalezienie parametrów, które odzwierciedlają wrażenie dźwięczności w barwie głosu. W artykule podjęto próbę dokładniejszego zdefiniowania co to jest dźwięczność w śpiewie i dźwięczny głos. Do oceny dźwięczności głosu śpiewaczego zostało wytypowanych dziesięć parametrów, obliczonych i porównanych z opiniami ekspertów oceniających dźwięczność w nagraniach śpiewu. Z uwagi na różnice w charakterystyce głosów męskich i żeńskich śpiewacy byli analizowani w osobnych grupach.

5

Audio database for the as sessment of singing voice quality of choir members

Łazoryszczak M., Półrolniczak E.

Elektronika : konstrukcje, technologie, zastosowania

|

2013

|

Vol. 54, nr 3

92-96

EN

The herewith article presents design aspects of audio database of choir signing voices. The aim of such a database as being designed is are sented, with its main assumptions and the method of its construction, ths process of creating the recordings and their preliminary processing included. Following this, the method of segmentation and storage of the source material is described with the inclusion of naming convention and data structure. Quantitative and qualitative characteristic of the sound data as obtained and the possibility of performing further studies are also an important part of the article.

PL

W artykule zaprezentowano aspekty projektowe dźwiękowej bazy danych głosów chóralnych. Przedstawiono cel, któremu projektowana baza ma służyć, główne założenia oraz sposób realizacji z uwzględnieniem procesu realizacji nagrań oraz ich obróbki wstępnej. Następnie opisano sposób segmentacji i przechowywania materiału źródłowego z uwzględnieniem konwencji nazewniczej i struktury danych. Istotnym elementem artykułu jest charakterystyka ilościowa i jakościowa pozyskanych danych dźwiękowych wraz ze wskazaniem możliwości realizacji dalszych badań.

6

Quality assessment of intonation of choir singers using F0 and trend lines for singing sequence

Półrolniczak E., Łazoryszczak M.

Metody Informatyki Stosowanej

|

2011

|

nr 4

259-268

EN

In this paper a part of quality assessment process of the intonation of singing voice is described. Intonation is understood here as the ability to precisely reproduce a given pitch. Such evaluation is typically performed by voice production experts (voice trainers) or other persons associated with singing. For the purpose of determining the quality of intonation an exercise performed by singers on subsequent pitches was proposed in the article. One of pitch extraction methods is used to determine the fundamental frequency and estimate the F0 trajectory. Based on the obtained trajectory, an attempt is made to determine a general trend among tested singers. It is also indicated, that it is possible to point out problems in singing for tested persons, which can be useful in further stages of voice training.

7

Automatyczne przetwarzanie nagrań dźwiękowych do celów analizy

Półrolniczak E., Kramarczyk M.

Metody Informatyki Stosowanej

|

2011

|

nr 5

233-240

EN

In this article the authors present the idea of automatic processing of singing recordings to create a database and for later analysis. The recordings contain sequences of sounds of the piano and singing separated by short segments of silence. The aim of the presented approach is the precise segmentation of the recordings and standardization of the resulting segments (termed further as samples) for later assessment of vocal quality. The taken approach can reduce the amount of time required for preparation of a database with sequences of singing for the analysis of singing voice quality. The samples obtained in the process must meet the prescribed requirements to enable carrying out the planned analyzes such as estimation of the fundamental frequency, vibrato estimation, Singing Power Ratio and formants estimation.

8

The impact of the type of sung vowels on the singing quality

Półrolniczak E., Łazoryszczak M., Mąka M.

Elektronika : konstrukcje, technologie, zastosowania

|

2011

|

Vol. 52, nr 11

112-114

EN

The paper presents an approach of assessment of singing quality based on properties of fundamental frequency (FO) trajectories. An analysis of singing has been performed using exercise with dedicated phrase containing consecutive vowels at the same pitch. The frequency deviations between voice's pitch and target tonality along with intonation trends have been considered at evaluation stage. Performed experiments show that in case of short duration of singing sounds, the vowel type is independent of whole phrase. The special case was/o/vowel which had decreasing trend in terms of intonation. Proposed technique of singing voice assessment is characterized by simplicity and low computational complexity, thus can be used in real-time applications.

PL

W pracy przedstawiono technikę oceny jakości głosu śpiewanego z wykorzystaniem własności trajektorii częstotliwości tonu krtaniowego (FO). Przeprowadzono analizę śpiewu z użyciem ćwiczenia, na które składala się fraza zawierająca samogłoski śpiewane kolejno na tej samej wysokości dźwięku. Wykorzystano pomiar odchylenia częstotliwości pomiędzy śpiewanymi i zadanymi dźwiękami. Przeprowadzone eksperymenty pokazują, że w sytuacji, gdy czas trwania śpiewanej głoski jest krótki to ich rodzaj nie miał znaczącego wpływu na całość frazy. Wyjątkiem była tu głoska /o/, która we wszystkich przypadkach wykazywała trend zniżkowy, jeśli chodzi o intonację. Proponowane podejście oceny głosu śpiewanego charakteryzuje się prostotą i niską złożoności obliczeniową, co stwarza możliwości jego wykorzystania w zastosowaniach czasu rzeczywistego.

9

Automatic singing quality recognition employing artificial neural networks

Żwan P.

Archives of Acoustics

|

2008

|

Vol. 33, No. 1

65-71

EN

The aim of the paper is to determine how quality of a singing voice can be recognized automatically. For this purpose, a database of singing voice sounds with samples of voices of trained and untrained singers was created and is presented. The methods of a singing voice parameterization are shortly reviewed and a set of descriptors is outlined. Each of the presented samples is parameterized and judged by experts, and the resulting feature vectors and quality scores are then used to train an artificial neural network. A comparison between experts' judgments and automatic recognition results is performed. Finally, statistical methods are applied to prove that an artificial neural network is able to automatically determine the quality of a singing voice with the accuracy very similar to expert assessments. The paper includes the discussion of results and presents derived conclusions.