Ha-Jin Yu

1.6k total citations · 1 hit paper
59 papers, 957 citations indexed

About

Ha-Jin Yu is a scholar working on Artificial Intelligence, Signal Processing and Computer Vision and Pattern Recognition. According to data from OpenAlex, Ha-Jin Yu has authored 59 papers receiving a total of 957 indexed citations (citations by other indexed papers that have themselves been cited), including 49 papers in Artificial Intelligence, 48 papers in Signal Processing and 8 papers in Computer Vision and Pattern Recognition. Recurrent topics in Ha-Jin Yu's work include Speech Recognition and Synthesis (49 papers), Speech and Audio Processing (44 papers) and Music and Audio Processing (36 papers). Ha-Jin Yu is often cited by papers focused on Speech Recognition and Synthesis (49 papers), Speech and Audio Processing (44 papers) and Music and Audio Processing (36 papers). Ha-Jin Yu collaborates with scholars based in South Korea, France and Finland. Ha-Jin Yu's co-authors include Hye-jin Shim, Jee-weon Jung, Minseok Kim, Hee-Soo Heo, Ju-ho Kim, Bong‐Jin Lee, Hemlata Tak, Nicholas Evans, Joon Son Chung and Hye-jin Shim and has published in prestigious journals such as IEEE Access, Sensors and Neural Networks.

In The Last Decade

Ha-Jin Yu

55 papers receiving 917 citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

AASIST: Audio Anti-Spoofing Using Integrated Spectro-Temporal Graph Attention Networks

2022 156 citations Jee-weon Jung, Hee-Soo Heo et al. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) profile →

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name	h						Papers	Cites
Ha-Jin Yu South Korea	15	697	614	184	76	55	59	957
Hyun Kwon South Korea	16	455 0.7×	216 0.4×	204 1.1×	94 1.2×	118 2.1×	73	714
Yangguang Liu China	11	220 0.3×	63 0.1×	96 0.5×	52 0.7×	43 0.8×	52	468
Mostafa Azizi Morocco	15	291 0.4×	157 0.3×	154 0.8×	112 1.5×	311 5.7×	72	759
Aziz Alotaibi Saudi Arabia	13	103 0.1×	119 0.2×	165 0.9×	84 1.1×	83 1.5×	34	427
Sobia Wassan China	8	338 0.5×	482 0.8×	93 0.5×	207 2.7×	419 7.6×	11	723
Xiaoxin Chen China	11	309 0.4×	165 0.3×	77 0.4×	197 2.6×	130 2.4×	40	567
Gen Zhang China	5	210 0.3×	80 0.1×	130 0.7×	33 0.4×	27 0.5×	14	460
Sheshang Degadwala India	17	409 0.6×	140 0.2×	376 2.0×	39 0.5×	32 0.6×	170	1.1k
Mingjie Li China	9	339 0.5×	113 0.2×	333 1.8×	45 0.6×	76 1.4×	13	619

Countries citing papers authored by Ha-Jin Yu

Since Specialization

Citations

This map shows the geographic impact of Ha-Jin Yu's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Ha-Jin Yu with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Ha-Jin Yu more than expected).

Fields of papers citing papers by Ha-Jin Yu

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Ha-Jin Yu. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Ha-Jin Yu. The network helps show where Ha-Jin Yu may publish in the future.

Co-authorship network of co-authors of Ha-Jin Yu

This figure shows the co-authorship network connecting the top 25 collaborators of Ha-Jin Yu. A scholar is included among the top collaborators of Ha-Jin Yu based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Ha-Jin Yu. Ha-Jin Yu is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

1.

Yu, Ha-Jin, et al.. (2024). A Deep Learning–Based Rotten Food Recognition App for Older Adults: Development and Usability Study. JMIR Formative Research. 8. e55342–e55342. 1 indexed citations

2.

Yu, Ha-Jin, et al.. (2023). SS-BSN: Attentive Blind-Spot Network for Self-Supervised Denoising with Nonlocal Self-Similarity. 800–809. 10 indexed citations

3.

Heo, Jungwoo, et al.. (2022). Extended U-Net for Speaker Verification in Noisy Environments. Interspeech 2022. 590–594. 7 indexed citations

4.

Jung, Jee-weon, Hemlata Tak, Hye-jin Shim, et al.. (2022). SASV 2022: The First Spoofing-Aware Speaker Verification Challenge. Interspeech 2022. 2893–2897. 26 indexed citations

5.

Kim, Ju-ho, et al.. (2022). RawNeXt: Speaker Verification System For Variable-Duration Utterances With Deep Layer Aggregation And Extended Dynamic Scaling Policies. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 7647–7651. 12 indexed citations

6.

Yu, Ha-Jin, et al.. (2021). Multiple-Point Input and Time-Inverted Speech Signal for The ASVspoof 2021 Challenge. 37–41. 5 indexed citations

7.

Jung, Jee-weon, Hee-Soo Heo, Hye-jin Shim, & Ha-Jin Yu. (2020). Knowledge Distillation in Acoustic Scene Classification. IEEE Access. 8. 166870–166879. 24 indexed citations

8.

Jung, Jee-weon, Hye-jin Shim, Ju-ho Kim, & Ha-Jin Yu. (2020). α-feature map scaling for raw waveform speaker verification. The Journal of the Acoustical Society of Korea. 39(5). 441–446. 1 indexed citations

9.

Jung, Jee-weon, et al.. (2020). Improved RawNet with Feature Map Scaling for Text-Independent Speaker Verification Using Raw Waveforms. 1496–1500. 62 indexed citations

10.

Jung, Jee-weon, et al.. (2020). Acoustic Scene Classification Using Audio Tagging. 1176–1180. 2 indexed citations

11.

Shim, Hye-jin, Hee-Soo Heo, Jee-weon Jung, & Ha-Jin Yu. (2020). Self-Supervised Pre-Training with Acoustic Configurations for Replay Spoofing Detection. 1091–1095. 5 indexed citations

12.

Jung, Jee-weon, Hee-Soo Heo, Ju-ho Kim, Hye-jin Shim, & Ha-Jin Yu. (2019). RawNet: Advanced End-to-End Deep Neural Network Using Raw Waveforms for Text-Independent Speaker Verification. 1268–1272. 94 indexed citations

13.

Heo, Hee-Soo, et al.. (2019). End-to-End Losses Based on Speaker Basis Vectors and All-Speaker Hard Negative Mining for Speaker Verification. 4035–4039. 15 indexed citations

14.

Heo, Hee-Soo, Jee-weon Jung, Hye-jin Shim, & Ha-Jin Yu. (2019). Acoustic Scene Classification Using Teacher-Student Learning with Soft-Labels. 614–618. 15 indexed citations

15.

Jung, Jee-weon, et al.. (2018). D-vector based speaker verification system using Raw Waveform CNN. 9 indexed citations

16.

Kim, Minseok, et al.. (2017). Histogram equalization using a reduced feature set of background speakers’ utterances for speaker recognition. Frontiers of Information Technology & Electronic Engineering. 18(5). 738–750. 3 indexed citations

17.

Heo, Hee-Soo, et al.. (2017). Applying compensation techniques on i-vectors extracted from short-test utterances for speaker verification using deep neural network. 5490–5494. 4 indexed citations

18.

Heo, Hee-Soo, et al.. (2016). Advanced b-vector system based deep neural network as classifier for speaker verification. 5465–5469. 4 indexed citations

19.

Kim, Minseok & Ha-Jin Yu. (2007). A New Feature Transformation Method Based on Rotation for Speaker Identification. iv. 68–73. 194 indexed citations

20.

Yu, Ha-Jin & Yujin Oh. (2000). A neural network for 500 word vocabulary word spotting using non-uniform units. Neural Networks. 13(6). 681–688.

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact