Science Explorer Back to mapMap
Discussion
Topic · Signal Processing

Speech and Audio Processing

Speech and Audio Processing is a research topic within Signal Processing. Science Explorer counts 64k research works in it since 1950. 9.9% of them reached the world's top 10% most cited for their field and year.

This cluster of papers focuses on the advances in speech enhancement techniques, including audio-visual speech recognition, deep learning methods, noise reduction, source separation, reverberation handling, objective quality measures, beamforming, and lipreading. The papers cover a wide range of topics related to improving the quality and intelligibility of speech signals in various challenging acoustic environments.

  • Speech Enhancement
  • Audio-Visual Speech Recognition
  • Deep Learning
  • Noise Reduction
  • Source Separation
  • Reverberation
  • Objective Quality Measures
  • Beamforming
  • Lipreading
  • Neural Networks
Research works
64k
fractional, since 1950
In the world top 10%
6.4k
per year above
Top-10% rate
9.9%
share of its works in the world top 10%
Growth, 2018-21 → 2022-25
+22%
the tick is no change
Largest producer
China
44% of the 10 largest, 2022-now
Speech and Audio Processing

Which countries lead Speech and Audio Processing research?

By volume, China and the United States publish the most (4.3k and 1.4k works in 2022-now).

By volume, 2022-now

  1. 1 China 4.3k works
  2. 2 United States 1.4k works
  3. 3 India 1.4k works
  4. 4 Japan 687 works
  5. 5 United Kingdom 471 works
  6. 6 South Korea 417 works
  7. 7 Germany 417 works
  8. 8 France 259 works
  9. 9 Taiwan 216 works
  10. 10 Canada 205 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: 43.9%United States: 14.7%India: 14.0%Japan: 7.1%6 others listed: 20.4%44%largest
China4,268 · 43.9%United States1,433 · 14.7%India1,361 · 14.0%Japan687 · 7.1%6 others listed1,985 · 20.4%

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

Which institutions lead Speech and Audio Processing research?

By volume in 2022-now, Chinese Academy of Sciences publishes the most Speech and Audio Processing research, followed by Northwestern Polytechnical University and Shanghai Jiao Tong University.

By volume, 2022-now

  1. 1 Chinese Academy of SciencesChina 203 works
  2. 2 Northwestern Polytechnical UniversityChina 130 works
  3. 3 Shanghai Jiao Tong UniversityChina 98 works
  4. 4 University of Science and Technology of ChinaChina 94 works
  5. 5 Centre National de la Recherche ScientifiqueFrance 88 works
  6. 6 University of Electronic Science and Technology of ChinaChina 82 works
  7. 7 Harbin Engineering UniversityChina 80 works
  8. 8 Zhejiang UniversityChina 76 works
  9. 9 Tsinghua UniversityChina 75 works
  10. 10 Beijing University of Posts and TelecommunicationsChina 60 works

Who are the leading researchers in Speech and Audio Processing?

The most-cited researchers publishing on Speech and Audio Processing include Yoshua Bengio, Geoffrey E. Hinton and Xiangyu Zhang.

  1. 1 Yoshua Bengio Canada 476k citations
  2. 2 Geoffrey E. Hinton Canada 454k citations
  3. 3 Xiangyu Zhang 327k citations
  4. 4 Xiaogang Wang China 260k citations
  5. 5 Yann LeCun United States 256k citations
  6. 6 Andrew Zisserman United Kingdom 255k citations
  7. 7 Li Fei-Fei United States 225k citations
  8. 8 Kai You Wang China 224k citations
  9. 9 Ilya Sutskever Canada 219k citations
  10. 10 Piotr Dollár Israel 211k 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 Speech and Audio Processing?

The most cited paper in Speech and Audio Processing is "Savitzky-Golay Smoothing Filters" (William H. Press, Saul A. Teukolsky, 1990), with 11,772 citations. Next come "Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups" (10,453) and "Librispeech: An ASR corpus based on public domain audio books" (6,112).

Most cited papers
#PaperReleasedCitations
1 Savitzky-Golay Smoothing Filters William H. Press, Saul A. Teukolsky · Computers in Physics Open access Nov 1990 11,772
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 Librispeech: An ASR corpus based on public domain audio books Vassil Panayotov, Guoguo Chen, Daniel Povey et al. Conference paper Apr 2015 6,112
4 Adaptive Mixtures of Local Experts Robert A. Jacobs, Michael I. Jordan, Steven J. Nowlan et al. · Neural Computation Feb 1991 5,316
5 Kaldi Speech Recognition Toolkit Daniel Povey · Infoscience (Ecole Polytechnique Fédérale de Lausanne) Open access 2024 4,890
All 100 most cited papers, with filters and sorting

Where is Speech and Audio Processing research done?

The largest centres of Speech and Audio Processing research in 2022-now are Beijing (China), Xi'an (China), Tokyo (Japan) and Shanghai (China). Among places with at least 20 works in it, it is an unusually large share of all research in Nomi Shi, Oldenburg and Redmond.

Largest cities, 2022-now

  1. 1 BeijingChina 840 works
  2. 2 Xi'anChina 317 works
  3. 3 TokyoJapan 303 works
  4. 4 ShanghaiChina 269 works
  5. 5 NanjingChina 266 works
  6. 6 SeoulSouth Korea 198 works
  7. 7 ChengduChina 182 works
  8. 8 HangzhouChina 169 works
  9. 9 WuhanChina 167 works
  10. 10 ShenzhenChina 162 works

Where it is the local speciality

  1. Nomi ShiJP · 21.4 works26×
  2. OldenburgDE · 49.8 works20×
  3. RedmondUS · 21.1 works18×
← less than its size predicts1×more →

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

See Speech and Audio Processing on the map

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

Among universities, judged by research, Nanyang Technological University, University of Science and Technology of China and Northwestern Polytechnical University score highest, combining citation 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 21.26%fractional works in this field (log) →share of work in the world top 10% →Nanyang Technologica…Chinese University o…University of Scienc…Northwestern Polytec…
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.

Citation 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 71.926.3%5.9×50 +66.1%
2University of Science and Technology of ChinaChina 68.217.9%7.4×94 +63.7%
3Northwestern Polytechnical UniversityChina 64.712.4%10.7×130 +23.7%
4Chinese University of Hong Kong, ShenzhenChina 64.323.6%10.8×21 +495.3%
5Shanghai Jiao Tong UniversityChina 63.114.3%3.2×98 +34.8%
6Carnegie Mellon UniversityUnited States 62.419.2%7.9×35 +15.6%
7Zhejiang UniversityChina 61.715.3%2.6×76 +100.4%
8Korea Advanced Institute of Science and TechnologySouth Korea 61.120.3%9.0×46 +22.4%
9Sardar Vallabhbhai National Institute of Technology SuratIndia 60.744.7%5.2×9 +151.5%
10Chinese University of Hong KongChina 60.018.6%3.5×27 +65.1%

Universities only. The score blends citation 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 Speech and Audio Processing, country by country

Is Speech and Audio Processing research growing?

Output in 2022-2025 was 22% higher than in 2018-2021, peaking in 2024. The fastest-growing topics are Speech 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 Speech and Audio Processing as a percentage of every work published that year, 0.059% in 2024.

still counting0.10%0.20%Speech and Audio Processing0.049% in 202519801990200020102020

Fractional works of Speech 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%Speech and Audio Processing9.6% 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 Speech and Audio Processing. Keep it to the research: no personal attacks, advertising or links. Any reader can report a post, which collapses it for everyone until it is opened.