Ehsan Variani

1.9k citations

22 papers · 1.1k indexed · 1 hit paper · h-index 11

Impact in

Signal Processing top 0.5%
- Speech and Audio Processing
- Music and Audio Processing
Artificial Intelligence top 1%
- Speech Recognition and Synthesis
- Natural Language Processing Techniques
- Topic Modeling
- Speech and dialogue systems

Papers in

Signal Processing 16
- Speech and Audio Processing 12
- Music and Audio Processing 11
Artificial Intelligence 21
- Speech Recognition and Synthesis 18
- Natural Language Processing Techniques 6
- Topic Modeling 3
- Algorithms and Data Compression 2
- Neural Networks and Applications 1

Co-authors: Erik McDermott Javier Gónzalez-Domínguez Ignacio López Moreno Xin Lei Michiel Bacchiani Tara N. Sainath Izhak Shafran Arun Narayanan
Journals: IEEE/ACM Transactions on Audio Speech and Language Processing (1 paper)ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (1 paper)Interspeech 2022 (2 papers)
Partner nations: United States

In The Last Decade

Ehsan Variani

22 papers receiving 1.0k citations

Hit Papers

align trajectories log scale

Deep neural networks for small footprint text-dependent speaker verification 2014 · 645 citations

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if any of the following hold:

it has ≥500 total citations;
it reaches ≥1.5× the top-1% citation threshold for papers in the same subfield and year (the threshold is the minimum needed to enter the top 1%, not the average within it);
it reaches the top citation threshold in at least one of its specific research topics.

2014 Deep neural networks for small footprint text-dependent speaker verification

Peers

Countries citing papers authored by Ehsan Variani

Since Specialization

Citations

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

Fields of papers citing papers by Ehsan Variani

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authors

The 25 scholars most cited alongside Ehsan Variani, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Ehsan Variani Line = papers co-authored together Ehsan Variani links everyone, so they are left out of the graph.

All Works

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

20 of 20 papers shown

#	Work
1	Alignment Entropy Regularization Ehsan Variani, 大和志保, David Rybach, Cyril Allauzen, Michael A. Riley	2023	1
2	Modular Hybrid Autoregressive Transducer Zhong Meng, Kap‐Joong Kim, Rohit Prabhavalkar, Yu Zhang, Gary Wang, Kartik Audhkhasi, N. Spatari, Trevor Strohman, Bhuvana Ramabhadran, Wei Huang, Ehsan Variani, Yinghui Huang, Pedro J. Moreno	2023	11
3	JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition Zhong Meng, Weiran Wang, Rohit Prabhavalkar, Tara N. Sainath, Kap‐Joong Kim, Ehsan Variani, Yu Zhang, Bo Li, Rong Ming, Bhuvana Ramabhadran	2023	4
4	Multilingual Second-Pass Rescoring for Automatic Speech Recognition Systems ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ·Neeraj Gaur, Kap‐Joong Kim, Ehsan Variani, Parisa Haghani, Bhuvana Ramabhadran, Pedro J. Moreno	2022	2
5	UserLibri: A Dataset for ASR Personalization Using Only Text Interspeech 2022 ·Muling Zhang, Yi-Wei Mal, Ehsan Variani, Josep Fornos, Rajiv Mathews, Khe Chai Sim, Dong-Woo Yun, Mingqing Chen, Elizabeth E. Alfane	2022	2
6	Improving Rare Word Recognition with LM-aware MWER Training Interspeech 2022 ·Weiran Wang, Tongzhou Chen, Tara N. Sainath, Ehsan Variani, Rohit Prabhavalkar, Wei Huang, Bhuvana Ramabhadran, Neeraj Gaur, Yaning Liu, 汪小凯 WANG Xiaokai, Trevor Strohman, Δήμητρης Ελευθέρογλου, David Rybach	2022	7
7	An Efficient Streaming Non-Recurrent On-Device End-to-End Model with Improvements to Rare-Word Modeling Tara N. Sainath, Δήμητρης Ελευθέρογλου, Arun Narayanan, 中共阿克苏市委党校新疆阿克苏, Ruoming Pang, David Rybach, Cyril Allauzen, Ehsan Variani, James Qin, Berit Brattne, Shuo-Yiin Chang, WD T, Anmol Gulati, Jiahui Yu, Chung‐Cheng Chiu, Diamantino Caseiro, M J Lochen, Zena Rudo, Claude de Moreau de Gerbehaye	2021	31
8	A Hybrid Seq-2-Seq ASR Design for On-Device and Server Applications Cyril Allauzen, Ehsan Variani, Michael Riley, David Rybach, Hao Zhang	2021	3
9	Neural Oracle Search on N-BEST Hypotheses Ehsan Variani, Kap‐Joong Kim, Cheri Yecke, Bhuvana Ramabhadran, Youngtak Cho, Pedro J. Moreno	2020	4
10	Efficient Implementation of the Room Simulator for Training Deep Neural Network Acoustic Models Chanwoo Kim, Ehsan Variani, Arun Narayanan, Michiel Bacchiani	2018	10
11	Sampled Connectionist Temporal Classification Ehsan Variani, Tom Bagby, Kamel Lahouel, Erik McDermott, Michiel Bacchiani	2018	6
12	Acoustic Modeling for Google Home Bo Li, Tara N. Sainath, Arun Narayanan, A.J. McMichael, Michiel Bacchiani, Ananya Misra, Izhak Shafran, Haşim Sak, Golan Pundak, K. K. Chin, Khe Chai Sim, Ron J. Weiss, Kevin Wilson, Ehsan Variani, Chanwoo Kim, Olivier Siohan, M. Weintraub, Erik McDermott, Richard C. Rose, Matt Shannon	2017	100
13	Multichannel Signal Processing With Deep Neural Networks for Automatic Speech Recognition IEEE/ACM Transactions on Audio Speech and Language Processing ·Tara N. Sainath, Ron J. Weiss, Kevin Wilson, Bo Li, Arun Narayanan, Ehsan Variani, Michiel Bacchiani, Izhak Shafran, Andrew Senior, K. K. Chin, Ananya Misra, Chanwoo Kim	2017	165
14	End-to-End Training of Acoustic Models for Large Vocabulary Continuous Speech Recognition with TensorFlow Ehsan Variani, Tom Bagby, Erik McDermott, Michiel Bacchiani	2017	12
15	Reducing the Computational Complexity of Multimicrophone Acoustic Models with Integrated Feature Extraction Tara N. Sainath, Arun Narayanan, Ron Weiss, Ehsan Variani, Kevin Wilson, Michiel Bacchiani, Izhak Shafran	2016	13
16	A Gaussian Mixture Model layer jointly optimized with discriminative features within a Deep Neural Network architecture Ehsan Variani, Erik McDermott, Georg Heigold	2015	29
17	Deep neural networks for small footprint text-dependent speaker verification Ehsan Variani, Xin Lei, Erik McDermott, Ignacio López Moreno, Javier Gónzalez-Domínguez Hit paper breakdown →	2014	645
18	Mean temporal distance: Predicting ASR error from temporal properties of speech signal Hynek Heřmanský, Ehsan Variani, Vijayaditya Peddinti	2013	29
19	Multi-stream recognition of noisy speech with performance monitoring Ehsan Variani, Feipeng Li, Hynek Heřmanský	2013	9
20	VTLN in the MFCC domain: band-limited versus local interpolation Ehsan Variani, Thomas Schaaf	2011	2

About Ehsan Variani

Ehsan Variani is a scholar working on Signal Processing, Artificial Intelligence, Hardware and Architecture, Computer Vision and Pattern Recognition and Computational Mechanics, having authored 22 papers that have together received 1.1k indexed citations. Recurring topics across this work include Speech Recognition and Synthesis (18 papers), Speech and Audio Processing (12 papers), Music and Audio Processing (11 papers), Natural Language Processing Techniques (6 papers), Topic Modeling (3 papers), Algorithms and Data Compression (2 papers), Neural Networks and Applications (1 paper) and Advanced Adaptive Filtering Techniques (1 paper). The work is most often cited by research in Signal Processing (884 citations), Artificial Intelligence (939 citations), Computer Vision and Pattern Recognition (83 citations), Computational Mechanics (63 citations) and Cognitive Neuroscience (38 citations). Ehsan Variani has collaborated with scholars based in United States. Frequent co-authors include Erik McDermott, Javier Gónzalez-Domínguez, Ignacio López Moreno, Xin Lei, Michiel Bacchiani, Tara N. Sainath, Izhak Shafran, Arun Narayanan, Chanwoo Kim and Kevin Wilson. Their work appears in journals such as IEEE/ACM Transactions on Audio Speech and Language Processing, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) and Interspeech 2022.

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