Frank Seide

9.1k total citations · 5 hit papers
95 papers, 4.3k citations indexed

About

Frank Seide is a scholar working on Artificial Intelligence, Signal Processing and Computer Vision and Pattern Recognition. According to data from OpenAlex, Frank Seide has authored 95 papers receiving a total of 4.3k indexed citations (citations by other indexed papers that have themselves been cited), including 85 papers in Artificial Intelligence, 47 papers in Signal Processing and 11 papers in Computer Vision and Pattern Recognition. Recurrent topics in Frank Seide's work include Speech Recognition and Synthesis (65 papers), Speech and Audio Processing (37 papers) and Music and Audio Processing (35 papers). Frank Seide is often cited by papers focused on Speech Recognition and Synthesis (65 papers), Speech and Audio Processing (37 papers) and Music and Audio Processing (35 papers). Frank Seide collaborates with scholars based in China, United States and Germany. Frank Seide's co-authors include Dong Yu, Gang Li, Chen Xie, Kaisheng Yao, Li Deng, Amit Agarwal, Jasha Droppo, Hao Fu, Hang Su and Peng Yu and has published in prestigious journals such as Proceedings of the IEEE, IEEE Transactions on Audio Speech and Language Processing and IEEE Transactions on Speech and Audio Processing.

In The Last Decade

Frank Seide

88 papers receiving 3.7k citations

Hit Papers

Conversational speech transcription using context-depende... 2011 2026 2016 2021 2011 2013 2011 2014 2013 100 200 300 400 500
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.

  1. Conversational speech transcription using context-dependent deep neural networks
    2011 599 citations Frank Seide, Gang Li et al. profile →
  2. Recent advances in deep learning for speech research at Microsoft
    2013 510 citations Li Deng, Jinyu Li et al. profile →
  3. Feature engineering in Context-Dependent Deep Neural Networks for conversational speech transcription
    2011 482 citations Frank Seide, Gang Li et al. profile →
  4. 1-bit stochastic gradient descent and its application to data-parallel distributed training of speech DNNs
    2014 439 citations Frank Seide, Hao Fu et al. profile →
  5. KL-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition
    2013 300 citations Dong Yu, Kaisheng Yao et al. profile →

Peers — A (Enhanced Table)

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

Name h Career Trend Papers Cites
Frank Seide China 24 3.5k 2.1k 765 275 227 95 4.3k
Bhuvana Ramabhadran United States 34 4.4k 1.3× 2.7k 1.3× 938 1.2× 205 0.7× 106 0.5× 220 5.6k
H. Gish United States 25 2.2k 0.6× 1.9k 0.9× 978 1.3× 164 0.6× 184 0.8× 86 3.2k
B.-H. Juang United States 27 3.0k 0.9× 2.5k 1.2× 969 1.3× 130 0.5× 116 0.5× 64 4.2k
Eng Siong Chng Singapore 33 3.2k 0.9× 3.2k 1.5× 768 1.0× 266 1.0× 100 0.4× 323 4.7k
Nelson Morgan United States 32 3.5k 1.0× 2.9k 1.4× 606 0.8× 141 0.5× 315 1.4× 119 4.8k
Alexander Waibel United States 21 2.2k 0.6× 1.4k 0.7× 852 1.1× 205 0.7× 88 0.4× 95 3.3k
Joe Frankel United Kingdom 18 1.3k 0.4× 1.1k 0.5× 571 0.7× 229 0.8× 191 0.8× 38 2.5k
Michael L. Seltzer United States 29 3.2k 0.9× 3.0k 1.4× 585 0.8× 240 0.9× 76 0.3× 99 4.4k
H. Bourlard Switzerland 26 2.1k 0.6× 1.8k 0.9× 695 0.9× 118 0.4× 71 0.3× 65 3.2k

Countries citing papers authored by Frank Seide

Since Specialization
Citations

This map shows the geographic impact of Frank Seide'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 Frank Seide with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Frank Seide more than expected).

Fields of papers citing papers by Frank Seide

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Frank Seide. 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 Frank Seide. The network helps show where Frank Seide may publish in the future.

Co-authorship network of co-authors of Frank Seide

This figure shows the co-authorship network connecting the top 25 collaborators of Frank Seide. A scholar is included among the top collaborators of Frank Seide 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 Frank Seide. Frank Seide is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

20 of 20 papers shown
1.
Feng, Tiantian, Yiteng Huang, Weipeng He, et al.. (2025). Directional Source Separation for Robust Speech Recognition on Smart Glasses. 1–5.
2.
Le, Manh Duc, et al.. (2023). Factorized Blank Thresholding for Improved Runtime Efficiency of Neural Transducers. 1–5. 2 indexed citations
3.
Jia, Junteng, et al.. (2022). Federated Domain Adaptation for ASR with Full Self-Supervision. Interspeech 2022. 536–540. 10 indexed citations
4.
Stolcke, Andreas & Frank Seide. (2018). Achieving Human Parity in Conversational Speech Recognition using CNTK and a GPU Farm. 1 indexed citations
5.
Xiong, Wayne, Jasha Droppo, Xuedong Huang, et al.. (2017). Toward Human Parity in Conversational Speech Recognition. IEEE/ACM Transactions on Audio Speech and Language Processing. 25(12). 2410–2423. 146 indexed citations
6.
Mohamed, Abdelrahman, Frank Seide, Dong Yu, et al.. (2015). Deep bi-directional recurrent networks over spectral windows. 78–83. 28 indexed citations
7.
Seide, Frank, Hao Fu, Jasha Droppo, Gang Li, & Dong Yu. (2014). 1-bit stochastic gradient descent and its application to data-parallel distributed training of speech DNNs. 1058–1062. 439 indexed citations breakdown →
8.
Yu, Dong, Michael L. Seltzer, Kaisheng Yao, et al.. (2014). An introduction to computational networks and the computational network toolkit (invited talk).. Conference of the International Speech Communication Association. 3 indexed citations
9.
Deng, Li, Jinyu Li, Jui-Ting Huang, et al.. (2013). Recent advances in deep learning for speech research at Microsoft. 8604–8608. 510 indexed citations breakdown →
10.
Yu, Dong, Frank Seide, & Gang Li. (2012). Conversational speech transcription using context-dependent deep neural networks. International Conference on Machine Learning. 1–2. 94 indexed citations
11.
Seide, Frank, Gang Li, & Dong Yu. (2011). Conversational speech transcription using context-dependent deep neural networks. 437–440. 599 indexed citations breakdown →
12.
Sha, Meng, et al.. (2010). Vocabulary and Language Model Adaptation Using just One File. International Conference on Acoustics, Speech, and Signal Processing. 2 indexed citations
13.
Sha, Meng, et al.. (2010). Vocabulary and language model adaptation using just one speech file. 5410–5413. 8 indexed citations
14.
Yu, Peng, et al.. (2006). Towards spoken-document retrieval for the internet. 415–422. 38 indexed citations
15.
Moraveji, Neema, et al.. (2006). DynaLine: A Non-Disruptive TV User Interface for Passive Browsing of Internet Video. 33(5). 556–8. 2 indexed citations
16.
Seide, Frank, et al.. (2004). Vocabulary-independent search in spontaneous speech. 1. I–253. 55 indexed citations
17.
Seide, Frank, Jian-Lai Zhou, & Li Deng. (2003). Coarticulation modeling by embedding a target-directed hidden trajectory model into HMM - MAP decoding and evaluation. 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).. 1. I–748. 16 indexed citations
18.
Chang, Eric, et al.. (2002). A system for spoken query information retrieval on mobile devices. IEEE Transactions on Speech and Audio Processing. 10(8). 531–541. 47 indexed citations
19.
Seide, Frank, et al.. (1998). Phonetic Modeling in the Philips Chinese Continuous-Speech Recognition System. 107(14). 1160–1166. 15 indexed citations
20.
Seide, Frank & A. Kellner. (1997). Towards an automated directory information system. 1327–1330. 19 indexed citations

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

Breakdown of academic impact, for papers by Bhuvana Ramabhadran Breakdown of academic impact, for papers by H. Gish Breakdown of academic impact, for papers by B.-H. Juang Breakdown of academic impact, for papers by Eng Siong Chng Breakdown of academic impact, for papers by Nelson Morgan Breakdown of academic impact, for papers by Alexander Waibel Breakdown of academic impact, for papers by Joe Frankel Breakdown of academic impact, for papers by Michael L. Seltzer Breakdown of academic impact, for papers by H. Bourlard
Rankless by CCL
2026