On Computer-Assisted Orchestration

Maresz, Yan

doi:10.1080/07494467.2013.774515

Cited by 19 publications

(22 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This value is considerably larger than the frame size of purely spec- tral features, such as spectral centroid, spectral flux, or mel-frequency cepstral coefficients (MFCCs). Indeed, the frame size of spectral features for machine listening is typically set to T = 23ms, i.e., 2 10 = 1024 samples at a sampling rate of 44, 1kHz [22,23].…”

Section: Role Of Temporal Context Tmentioning

confidence: 99%

See 1 more Smart Citation

Time–frequency scattering accurately models auditory similarities between instrumental playing techniques

Lostanlen

El-Hajj

Rossignol³

et al. 2021

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

Instrumentalplaying techniques such as vibratos, glissandos, and trills often denote musical expressivity, both in classical and folk contexts. However, most existing approaches to music similarity retrieval fail to describe timbre beyond the so-called “ordinary” technique, use instrument identity as a proxy for timbre quality, and do not allow for customization to the perceptual idiosyncrasies of a new subject. In this article, we ask 31 human participants to organize 78 isolated notes into a set of timbre clusters. Analyzing their responses suggests that timbre perception operates within a more flexible taxonomy than those provided by instruments or playing techniques alone. In addition, we propose a machine listening model to recover the cluster graph of auditory similarities across instruments, mutes, and techniques. Our model relies on joint time–frequency scattering features to extract spectrotemporal modulations as acoustic features. Furthermore, it minimizes triplet loss in the cluster graph by means of the large-margin nearest neighbor (LMNN) metric learning algorithm. Over a dataset of 9346 isolated notes, we report a state-of-the-art average precision at rank five (AP@5) of .%. An ablation study demonstrates that removing either the joint time–frequency scattering transform or the metric learning algorithm noticeably degrades performance.

show abstract

Section: Role Of Temporal Context Tmentioning

confidence: 99%

“…Behind the overarching challenge of coming up with a robust predictive model for listening behaviors in humans, the main practical application of timbre similarity retrieval lies in the emerging topic of computer-assisted orchestration [ 10 ]. In such context, the composer queries the software with an arbitrary audio signal.…”

Section: Introductionmentioning

confidence: 99%

Time–frequency scattering accurately models auditory similarities between instrumental playing techniques

Lostanlen

El-Hajj

Rossignol³

et al. 2021

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

show abstract

“…As such, music research communities have converged to the creation of the emerging field of Music Information Retrieval (MIR). In a few years, with the improvement of computers and the advancements in machine learning techniques, the MIR field has brought impressive results in many directions and has been able to address problems that appeared to be unsolvable only 20 years ago, such as cover song identification (Serrà, 2011), structure analysis (Paulus et al, 2010), or automatic orchestration (Maresz, 2013;Pachet, 2016). It has been possible to develop technologies that allow users to understand, access, and explore music in all its different dimensions, from browsing personal collections, to managing the rights of music creators or to answering new musicological questions, at a level of abstraction and a scale that were previously not possible without the help of AI.…”

Section: A Brief History Of Mirmentioning

confidence: 99%

Learning, Probability and Logic: Toward a Unified Approach for Content-Based Music Information Retrieval

Crayencour

Cella

2019

Front. Digit. Humanit.

View full text Add to dashboard Cite

“…In the context of music creation, the query x(t) may be an instrumental or vocal sketch, a sound event recorded from the environment, a computer-generated waveform, or any mixture of the above [43]. Upon inspecting the recordings returned by the search engine, the composer may decide to retain one of the retrieved notes.…”

Section: Application Setting and Evaluationmentioning

confidence: 99%

“…One major cause of this gap in research is the di culty of collecting and annotating data for contemporary instrumental techniques. Fortunately, this obstacle has recently been overcome, owing to the creation of databases of instrumental samples for music orchestration in spectral music [43]. In this work, we capitalize on the availability of this data to formulate a new line of research in MIR, namely the joint retrieval of organological ("what instrument is being played in this recording?")…”

Section: Introductionmentioning

confidence: 99%

Extended playing techniques: The next milestone in musical instrument recognition

Lostanlen,

Andén,

Lagrange

2018

Preprint

View full text Add to dashboard Cite

e expressive variability in producing a musical note conveys information essential to the modeling of orchestration and style. As such, it plays a crucial role in computer-assisted browsing of massive digital music corpora. Yet, although the automatic recognition of a musical instrument from the recording of a single "ordinary" note is considered a solved problem, automatic identi cation of instrumental playing technique (IPT) remains largely underdeveloped. We benchmark machine listening systems for query-by-example browsing among 143 extended IPTs for 16 instruments, amounting to 469 triplets of instrument, mute, and technique. We identify and discuss three necessary conditions for signi cantly outperforming the traditional mel-frequency cepstral coe cient (MFCC) baseline: the addition of second-order sca ering coe cients to account for amplitude modulation, the incorporation of long-range temporal dependencies, and metric learning using large-margin nearest neighbors (LMNN) to reduce intra-class variability. Evaluating on the Studio On Line (SOL) dataset, we obtain a precision at rank 5 of 99.7% for instrument recognition (baseline at 89.0%) and of 61.0% for IPT recognition (baseline at 44.5%). We interpret this gain through a qualitative assessment of practical usability and visualization using nonlinear dimensionality reduction.

show abstract

On Computer-Assisted Orchestration

Cited by 19 publications

References 2 publications

Time–frequency scattering accurately models auditory similarities between instrumental playing techniques

Time–frequency scattering accurately models auditory similarities between instrumental playing techniques

Learning, Probability and Logic: Toward a Unified Approach for Content-Based Music Information Retrieval

Extended playing techniques: The next milestone in musical instrument recognition

Contact Info

Product

Resources

About