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. 13.8% 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%
- 8.9k per year above
- Top-10% rate
- 13.8% share of its works in the world top 10%
- Growth, 2013–17 → 2018–22
- +12% the tick is no change
Which countries lead Speech and Audio Processing research?
By volume, China and the United States publish the most (3.8k and 1.3k works in 2022–2025).
By volume, 2022–2025
- 1 China 3.8k works
- 2 United States 1.3k works
- 3 India 1.3k works
- 4 Japan 646 works
- 5 United Kingdom 444 works
- 6 Germany 380 works
- 7 South Korea 377 works
- 8 France 238 works
- 9 Taiwan 205 works
- 10 Canada 188 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.
Shares of the rows listed above, not of the whole node.
Which institutions lead Speech and Audio Processing research?
By volume in 2022–2025, Northwestern Polytechnical University publishes the most Speech and Audio Processing research, followed by Shanghai Jiao Tong University and University of Science and Technology of China.
By volume, 2022–2025
- 1 Northwestern Polytechnical University China 121 works
- 2 Shanghai Jiao Tong University China 89 works
- 3 University of Science and Technology of China China 85 works
- 4 University of Electronic Science and Technology of China China 78 works
- 5 Harbin Engineering University China 77 works
- 6 Zhejiang University China 67 works
- 7 Tsinghua University China 67 works
- 8 Chinese Academy of Sciences China 64 works
- 9 Institute of Acoustics China 61 works
- 10 Beijing University of Posts and Telecommunications China 55 works
Who are the leading researchers in Speech and Audio Processing?
The most-cited researchers publishing on Speech and Audio Processing include Andrew Zisserman, Yoshua Bengio and H. Vincent Poor.
- 1 Andrew Zisserman 25k citations
- 2 Yoshua Bengio 17k citations
- 3 H. Vincent Poor 9.5k citations
- 4 Thomas S. Huang 7.4k citations
- 5 Trevor Darrell 6.7k citations
- 6 Dacheng Tao 6.1k citations
- 7 Alex Pentland 6k citations
Ranked by citations received across their whole record, among researchers with at least three works on this topic.
Where is Speech and Audio Processing research done?
The largest centres of Speech and Audio Processing research in 2022–2025 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 Richardson.
Largest cities, 2022–2025
Where it is the local speciality
- Nomi ShiJP · 20.3 works25×
- OldenburgDE · 43.7 works19×
- RichardsonUS · 30.5 works12×
Location quotient: how much more of its research is in Speech and Audio Processing than the world average.
Where is the best place to study Speech and Audio Processing?
Among universities, judged by research, Northwestern Polytechnical University, Chinese University of Hong Kong, Shenzhen and Harbin Engineering University 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.
One dot per university in the table below. The upper left is the interesting corner: small places doing unusually strong work.
| # | University | Score | Top 10% | Specialisation | Works | Growth |
|---|---|---|---|---|---|---|
| 1 | Northwestern Polytechnical University China | 58.7 | 17.3% | 9.4× | 121 | +14.0% |
| 2 | Chinese University of Hong Kong, Shenzhen China | 57.6 | 34.0% | 8.6× | 18 | — |
| 3 | Harbin Engineering University China | 56.1 | 15.3% | 13.2× | 77 | +30.4% |
| 4 | Shenzhen Research Institute of Big Data China | 55.2 | 32.1% | 37.7× | 8 | — |
| 5 | The University of Texas at Dallas United States | 54.7 | 25.5% | 13.5× | 30 | -2.8% |
| 6 | Inner Mongolia University China | 54.3 | 14.9% | 9.1× | 22 | +287.1% |
| 7 | Dhirubhai Ambani University India | 53.2 | 23.0% | 81.1× | 19 | +84.4% |
| 8 | Institut National de la Recherche Scientifique Canada | 53.2 | 28.5% | 18.7× | 16 | -22.1% |
| 9 | University of Science and Technology of China China | 52.9 | 23.7% | 6.4× | 85 | +30.6% |
| 10 | Aalto University Finland | 52.3 | 14.2% | 10.0× | 34 | -6.8% |
Universities only. Score blends excellence (30%), specialisation (25%), size (20%), growth (15%) and international reach (10%), 2015–2022; growth compares 2010–14 with 2015–19.
Is Speech and Audio Processing research growing?
Output in 2018–2022 was 12% higher than in 2013–2017, peaking in 2024. The fastest-growing topics are Speech and Audio Processing.
The same series as a ribbon — one cell per year, darker for more. The line above answers how much; this answers when.
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.