Science Explorer Back to mapMap
Discussion
Topic · Signal Processing

Music and Audio Processing

Music and Audio Processing is a research topic within Signal Processing. Science Explorer counts 37k research works in it since 1950. 9.8% of them reached the world's top 10% most cited for their field and year.

This cluster of papers focuses on the classification and analysis of audio signals, including music genre classification, environmental sound recognition, melody extraction, and acoustic scene classification. It explores techniques such as deep learning, convolutional neural networks, and feature extraction for music information retrieval.

  • Audio Signal Classification
  • Music Information Retrieval
  • Deep Learning
  • Convolutional Neural Networks
  • Feature Extraction
  • Environmental Sound Recognition
  • Music Genre Classification
  • Melody Extraction
  • Acoustic Scene Classification
  • Audio Event Detection
Research works
37k
fractional, since 1950
In the world top 10%
3.6k
per year above
Top-10% rate
9.8%
share of its works in the world top 10%
Growth, 2018-21 → 2022-25
+32%
the tick is no change
Largest producer
China
36% of the 10 largest, 2022-now
Music and Audio Processing

Which countries lead Music and Audio Processing research?

By volume, China and India publish the most (2.4k and 1.2k works in 2022-now).

By volume, 2022-now

  1. 1 China 2.4k works
  2. 2 India 1.2k works
  3. 3 United States 1.1k works
  4. 4 Japan 442 works
  5. 5 United Kingdom 364 works
  6. 6 South Korea 291 works
  7. 7 Germany 279 works
  8. 8 France 241 works
  9. 9 Italy 195 works
  10. 10 Canada 172 works

How concentrated that is

The same countries as shares of everything the list above accounts for. A node where two countries do two thirds of the work and one spread evenly across twelve read alike as a ranking and not at all alike here.

China: 36.1%India: 18.0%United States: 16.5%Japan: 6.5%6 others listed: 22.8%36%largest
China2,440 · 36.1%India1,218 · 18.0%United States1,117 · 16.5%Japan442 · 6.5%6 others listed1,541 · 22.8%

Shares of the rows listed above, not of the whole node.

Which institutions lead Music and Audio Processing research?

By volume in 2022-now, Centre National de la Recherche Scientifique publishes the most Music and Audio Processing research, followed by Chinese Academy of Sciences and Medical Library Association.

By volume, 2022-now

  1. 1 Centre National de la Recherche ScientifiqueFrance 82 works
  2. 2 Chinese Academy of SciencesChina 73 works
  3. 3 Medical Library AssociationUnited States 68 works
  4. 4 Shanghai Jiao Tong UniversityChina 54 works
  5. 5 University of Science and Technology of ChinaChina 50 works
  6. 6 Tsinghua UniversityChina 47 works
  7. 7 Amrita Vishwa VidyapeethamIndia 45 works
  8. 8 Zhejiang UniversityChina 41 works
  9. 9 Queen Mary University of LondonUnited Kingdom 40 works
  10. 10 Vellore Institute of Technology UniversityIndia 37 works

Who are the leading researchers in Music and Audio Processing?

The most-cited researchers publishing on Music and Audio Processing include Yoshua Bengio, Geoffrey E. Hinton and Jun Wang.

  1. 1 Yoshua Bengio Canada 476k citations
  2. 2 Geoffrey E. Hinton Canada 454k citations
  3. 3 Jun Wang China 340k citations
  4. 4 Karl John Friston United Kingdom 310k citations
  5. 5 Jeremy Grimshaw Canada 281k citations
  6. 6 Xiaogang Wang China 260k citations
  7. 7 Yann LeCun United States 256k citations
  8. 8 Andrew Zisserman United Kingdom 255k citations
  9. 9 Li Fei-Fei United States 225k citations
  10. 10 Kai You Wang China 224k citations

Ranked by citations received across their whole record, among researchers with at least three works on this topic.

What are the most cited papers in Music and Audio Processing?

The most cited paper in Music and Audio Processing is "Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling" (Jun‐Young Chung, Çağlar Gülçehre, Kyunghyun Cho et al., 2014), with 10,801 citations. Next come "Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups" (10,453) and "Speech recognition with deep recurrent neural networks" (8,969).

Most cited papers
#PaperReleasedCitations
1 Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling Jun‐Young Chung, Çağlar Gülçehre, Kyunghyun Cho et al. · arXiv (Cornell University) PreprintOpen access 11 Dec 2014 10,801
2 Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups Geoffrey E. Hinton, Li Deng, Dong Yu et al. · IEEE Signal Processing Magazine 19 Oct 2012 10,453
3 Speech recognition with deep recurrent neural networks Alex M Graves, Abdelrahman Mohamed, Geoffrey E. Hinton Conference paper May 2013 8,969
4 LSTM: A Search Space Odyssey Klaus Greff, Rupesh Kumar Srivastava, Jan Koutník et al. · IEEE Transactions on Neural Networks and Learning Systems Open access 14 Jul 2016 7,047
5 Librispeech: An ASR corpus based on public domain audio books Vassil Panayotov, Guoguo Chen, Daniel Povey et al. Conference paper Apr 2015 6,112
All 100 most cited papers, with filters and sorting

Where is Music and Audio Processing research done?

The largest centres of Music and Audio Processing research in 2022-now are Beijing (China), Tokyo (Japan), Shanghai (China) and Seoul (South Korea). Among places with at least 20 works in it, it is an unusually large share of all research in Guildford.

Largest cities, 2022-now

  1. 1 BeijingChina 468 works
  2. 2 TokyoJapan 192 works
  3. 3 ShanghaiChina 162 works
  4. 4 SeoulSouth Korea 142 works
  5. 5 ChennaiIndia 117 works
  6. 6 Xi'anChina 116 works
  7. 7 LondonUnited Kingdom 115 works
  8. 8 ShenzhenChina 92 works
  9. 9 NanjingChina 90 works
  10. 10 WuhanChina 89 works

Where it is the local speciality

  1. GuildfordGB · 25.2 works9.9×
← less than its size predicts1×more →

Location quotient: how much more of its research is in Music and Audio Processing than the world average.

See Music and Audio Processing on the map

Where is the best place to study Music and Audio Processing?

Among universities, judged by research, Nanyang Technological University, Shanghai Jiao Tong University and University of Science and Technology of China score highest, combining excellence, specialisation, size, growth and international reach. Research strength is one signal when choosing where to study; it does not measure teaching.

0%20%40%mean 22.91%fractional works in this field (log) →share of work in the world top 10% →Nanyang Technologica…Carnegie Mellon Univ…University of Scienc…Shanghai Jiao Tong U…
above the meannear itbelow it

One dot per university in the first ten of the table below, at the default weights. The upper left is the interesting corner: small places doing unusually strong work.

Excellenceshare of its work in the world top 10%, 2022-now and all time averaged
40%
Specialisationhow much of its work is in this field, counted up to 10× the world share
10%
Sizeits output in this field, on a log scale
30%
Growthoutput growth, counted from -20% to +20%
10%
Internationalshare of its work with a co-author abroad
10%
Each slider sets a weight; the share it gets of the score is beside it.
#UniversityScoreTop 10%SpecialisationWorksGrowth
1Nanyang Technological UniversitySingapore 72.125.2%4.3×27 +96.6%
2Shanghai Jiao Tong UniversityChina 70.818.2%2.4×54 +76.9%
3University of Science and Technology of ChinaChina 70.819.4%5.3×50 +86.3%
4Carnegie Mellon UniversityUnited States 67.621.0%10.7×35 +0.6%
5University of SurreyUnited Kingdom 67.222.8%12.9×25 +6.3%
6Zhejiang UniversityChina 65.818.9%1.9×41 +175.6%
7Singapore University of Technology and DesignSingapore 65.436.4%11.1×8 +6.3%
8Korea Advanced Institute of Science and TechnologySouth Korea 64.917.6%9.3×34 +33.0%
9Chinese University of Hong KongChina 60.818.7%3.2×18 +47.5%
10Monash UniversityAustralia 60.730.9%1.7×13 +127.4%

Universities only. The score blends excellence (40%), size (30%), specialisation (10%), growth (10%), international reach (10%), 2022-now; growth compares 2018-21 with 2022-25 and counts up to +20%, since a jump from a small base is mostly noise.

Every institution in Music and Audio Processing, country by country

Is Music and Audio Processing research growing?

Output in 2022-2025 was 32% higher than in 2018-2021, peaking in 2023. The fastest-growing topics are Music and Audio Processing.

still counting19801990200020102020
grewheldshrank

The same series as a ribbon: one cell per year, darker for more. The line above answers how much; this answers when.

Its share of all research

Growing output can still be a shrinking share: all of science grows. This is Music and Audio Processing as a percentage of every work published that year, 0.040% in 2024.

still counting0.020%0.040%0.060%Music and Audio Processing0.034% in 202519801990200020102020

Fractional works of Music and Audio Processing over all fractional works that year. How the balance of science has shifted.

How much of it reaches the world top 10%

Year by year.

still counting5%10%15%Music and Audio Processing10.0% in 2025200020102020

Of each year's works in it, the share that reached the world's 10% most cited for their field and year. A field is the world for its own topics, so there is no other line to hold it against.

Which topics inside it are moving

Growth and decline on one axis around a shared zero. Two lists side by side hide the thing that matters: whether the growth dwarfs the decline, or the other way round.

Discussion

Ask a question or share a note about Music and Audio Processing. Posts are plain text and can be reported.