Wyniki wyszukiwania - BazTech

1

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.

2

Design and preliminary testing of the test apparatus to analyse the impact of hearing problems on the ability to repeat sound by singer

Kramarczyk M., Półrolniczak E.

Journal of Theoretical and Applied Computer Science

|

2015

|

Vol. 9, nr 3

3--8

EN

It is likely that serious hearing loss affect drastically human possibility of repeating the sounds. Remains the question of whether and how the delicate hearing loss affect the person’s ability to repeat sounds. Therefore we try to create the database samples singing, expanded on the tests of hearing for individual sigers, that could be used to further research in this direction. The studies were used two research stations one for the hearing test, and a second used to test the ability of the singer to repeat sound. First station used for hearing tests utilized a standard, certified audiometric cabin with cooperating with her professional audiometer. The second test station was design for record and analyse singers ability to repeat sound. Projected solution, use tools for both generate, playback and recording audio, with used adittional materials to improve the acoustic performance of the tests. This article describes the design of test aparature and presents the conclusions of the preeliminary tests, in particular those related to the second set of equipment.

3

Speech emotion recognition system for social robots

Juszkiewicz Ł.

Journal of Automation Mobile Robotics and Intelligent Systems

|

2013

|

Vol. 7, No. 4

59--65

EN

The paper presents a speech emotion recognition system for social robots. Emotions are recognised using global acoustic features of the speech. The system implements the speech parameters calculation, features extraction, features selection and classification. All these phases are described. The system was verified using the two emotional speech databases: Polish and German. Perspectives for using such system in the social robots are presented.

4

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.

5

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.

6

Selected quasi-lexical and non-lexical units in Polish map task dialogues

Karpiński M.

Archives of Acoustics

|

2007

|

Vol. 32, No. 1

51-65

EN

The present study is focused on selected types of fillers, quasi-words and non-lexical words that are generally categorized as expressing positive or negative response in Polish task-oriented dialogues. Basic phonetic properties of such units are analyzed with a special focus on intonation. Some of their possible realizations are shown and some relations between their intonational form and meaning are hypothesized. A brief note on comparative background from our recent work is also provided and some implications for speech technology are mentioned.