Timbre identification of instrumental music via energy distribution modeling

Guo, Jianmin; Ding, Mengying; Guan, Xiaohong; Du, Youtian; Feng, Jicheng; Gao, Qinping; Liu, Zheng

doi:10.1145/2808492.2808559

Cited by 3 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Energy is a measure of amount of sound produced by reed vibration. Previous studies [4,10] present that the distribution of energy and symmetry of reed in vibration accounts for tone quality. The symmetry of reed in vibration results in periodicity in signal, so we consider a representation associated with harmonics and noise, indicating periodic and non-periodic parts separately.…”

Section: Harmonic Energy Featuresmentioning

confidence: 98%

“…Hsiao et al [9] analyzed the waveform-shape-based features of saxophone, whereas systematical investigation is not conducted arXiv:2003.00414v1 [cs.SD] 1 Mar 2020 on the belief that tone quality relies on the richness of harmonics in frequency domain. Guo et al [10] constructed a one-dimension feature from energy distribution but without clarifying the relation to timbre. In addition, researchers have attempted to evaluate physical structures in a clarinet using optical holography [4] and investigated instrumental performance techniques [5,6] as well as the timbre of instruments such as bright, sweet, thick and transparent [7,8].…”

Section: Relation To Prior Workmentioning

confidence: 99%

“…The efforts were made on influence of physical components [4], and instrument controlling skills in rendition [5,6] and tone colors in music context [7,8]. The studies on the evaluation of saxophone timbre were considered as lack of systematic understanding of how the features con-tribute to tone quality [9][10][11]. In [12], Chavez et al showed that the clarinet tone quality is distinguishable visually via spectrogram, and in [13] the image representation by a popular convolutional neural network (CNN) structure, AlexNet, is analyzed with an average accuracy of 76.56%.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Harmonics Based Representation in Clarinet Tone Quality Evaluation

Wang

Guan

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Music tone quality evaluation is generally performed by experts. It could be subjective and short of consistency and fairness as well as time-consuming. In this paper we present a new method for identifying the clarinet reed quality by evaluating tone quality based on the harmonic structure and energy distribution. We first decouple the quality of reed and clarinet pipe based on the acoustic harmonics, and discover that the reed quality is strongly relevant to the even parts of the harmonics. Then we construct a features set consisting of the even harmonic envelope and the energy distribution of harmonics in spectrum. The annotated clarinet audio data are recorded from 3 levels of performers and the tone quality is classified by machine learning. The results show that our new method for identifying low and medium high tones significantly outperforms previous methods.

show abstract

Section: Harmonic Energy Featuresmentioning

confidence: 98%

Section: Relation To Prior Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Harmonics Based Representation in Clarinet Tone Quality Evaluation

Wang

Guan

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Computer-aided music understanding is mainly applied in inferring musical form, music genres, music styles and music types [6]. Guo et al presented a new approach to the instrumental tone quality analysis that can evaluate the level of the performer by instrumental tone quality recognition [7]. This paper focuses on the analysis of tone quality of wind instruments, and evaluates the quality level of wind instruments through the recognition results of tone quality.…”

Section: Introductionmentioning

confidence: 99%

Tone Quality Recognition of Instruments Based on Multi-feature Fusion of Music Signal

Lei¹,

Ding²,

Guan

et al. 2016

AJNC

View full text Add to dashboard Cite

The traditional expert-based instrumental music evaluation strategy can't meet the requirements of the rapidly accumulated audio data. The traditional strategy not only takes a high cost of human's energy and time but also may have some problems on consistency and fairness of judgment. This paper aims at designing a complete recognition and evaluation strategy to automatically identify the timber of wind instruments. We take the clarinet as example and propose a strategy based on multi-feature fusion and random forest. First, we use the identification of fundamental frequency algorithm to automatically distinguish the notes performed by the instruments. Second, we extract 3 types of features including MFCC, brightness and roughness to describe the instrumental signals. Then, considering two kinds of variants: note and tone quality, we design 5 strategies to remove the influence of different notes in the evaluation of tone quality. By analyzing these strategies, we explore the optimal strategy for the recognition. The final evaluation results over 840 music slices demonstrate the effectiveness of this method.

show abstract

Harmonics Based Representation in Clarinet Tone Quality Evaluation

Wang

Guan

et al. 2020

Preprint

View full text Add to dashboard Cite

Timbre identification of instrumental music via energy distribution modeling

Cited by 3 publications

References 6 publications

Harmonics Based Representation in Clarinet Tone Quality Evaluation

Harmonics Based Representation in Clarinet Tone Quality Evaluation

Tone Quality Recognition of Instruments Based on Multi-feature Fusion of Music Signal

Harmonics Based Representation in Clarinet Tone Quality Evaluation

Contact Info

Product

Resources

About