Daniel Povey
Impact in
- Signal Processing top 0.01%
- Speech and Audio Processing
- Music and Audio Processing
- Artificial Intelligence top 0.01%
- Speech Recognition and Synthesis
- Natural Language Processing Techniques
- Topic Modeling
- Speech and dialogue systems
Papers in
-
- Speech Recognition and Synthesis 163
- Natural Language Processing Techniques 55
- Topic Modeling 18
- Speech and dialogue systems 16
- Algorithms and Data Compression 6
-
- Speech and Audio Processing 104
- Music and Audio Processing 76
- Co-authors
- Sanjeev Khudanpur (81 shared papers)Guoguo Chen (10 shared papers)David Snyder (14 shared papers)Vijayaditya Peddinti (11 shared papers)Daniel Garcia-Romero (12 shared papers)Philip C. Woodland (10 shared papers)Gregory Sell (9 shared papers)Tom Ko (4 shared papers)
- Journals
- Computer Speech & Language (4 papers)IEEE/ACM Transactions on Audio Speech and Language Processing (3 papers)IEEE Transactions on Audio Speech and Language Processing (2 papers)IEEE Signal Processing Letters (2 papers)IEEE Transactions on Speech and Audio Processing (1 paper)
- Partner nations
- United StatesChinaUnited Kingdom
In The Last Decade
Daniel Povey
174 papers receiving 14.3k citations
Daniel Povey's Hit Papers
Peers
Comparison fields: 5 of 151
- Signal Processing 10.9k
- Artificial Intelligence 14.0k
- Experimental and Cognitive Psychology 958
- Computer Vision and Pattern Recognition 1.4k
- Human-Computer Interaction 103
Countries citing papers authored by Daniel Povey
This map shows the geographic impact of Daniel Povey'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 Daniel Povey with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Daniel Povey more than expected).
Fields of papers citing papers by Daniel Povey
This network shows the impact of papers produced by Daniel Povey. 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 Daniel Povey. The network helps show where Daniel Povey may publish in the future.
Co-authors
The 25 scholars most cited alongside Daniel Povey, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
Showing the 20 most-cited of 179 papers — load more, or switch the sort, to bring in the rest.
| # | Work | ||
|---|---|---|---|
| 1 | Librispeech: An ASR corpus based on public domain audio books Hit paper breakdown → | 2015 | 3449 |
| 2 | X-Vectors: Robust DNN Embeddings for Speaker Recognition Hit paper breakdown → | 2018 | 1542 |
| 3 | Audio augmentation for speech recognition Hit paper breakdown → | 2015 | 715 |
| 4 | A time delay neural network architecture for efficient modeling of long temporal contexts Hit paper breakdown → | 2015 | 610 |
| 5 | A study on data augmentation of reverberant speech for robust speech recognition Hit paper breakdown → | 2017 | 521 |
| 6 | Minimum Phone Error and I-smoothing for improved discriminative training Hit paper breakdown → | 2002 | 470 |
| 7 | Deep Neural Network Embeddings for Text-Independent Speaker Verification Hit paper breakdown → | 2017 | 460 |
| 8 | Sequence-discriminative training of deep neural networks Hit paper breakdown → | 2013 | 460 |
| 9 | Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI Hit paper breakdown → | 2016 | 458 |
| 10 | The HTK book version 3.4 | 2006 | 430 |
| 11 | Strategies for training large scale neural network language models Hit paper breakdown → | 2011 | 331 |
| 12 | Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks Hit paper breakdown → | 2018 | 283 |
| 13 | 2008 | 250 | |
| 14 | Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on | 2012 | 237 |
| 15 | 2002 | 221 | |
| 16 | 2016 | 213 | |
| 17 | 2010 | 210 | |
| 18 | 2014 | 202 | |
| 19 | 2006 | 196 | |
| 20 | 2019 | 186 |
About Daniel Povey
Daniel Povey is a scholar working on Artificial Intelligence, Signal Processing, Computer Vision and Pattern Recognition, Control and Systems Engineering and Experimental and Cognitive Psychology, having authored 179 papers that have together received 16.1k indexed citations. Recurring topics across this work include Speech Recognition and Synthesis (163 papers), Speech and Audio Processing (104 papers), Music and Audio Processing (76 papers), Natural Language Processing Techniques (55 papers), Topic Modeling (18 papers), Speech and dialogue systems (16 papers), Advanced Data Compression Techniques (10 papers) and Algorithms and Data Compression (6 papers). The work is most often cited by research in Signal Processing (10.9k citations), Artificial Intelligence (14.0k citations), Experimental and Cognitive Psychology (958 citations), Computer Vision and Pattern Recognition (1.4k citations) and Human-Computer Interaction (103 citations). Daniel Povey has collaborated with scholars based in United States, China and United Kingdom. Frequent co-authors include Sanjeev Khudanpur, Guoguo Chen, David Snyder, Vijayaditya Peddinti, Daniel Garcia-Romero, Philip C. Woodland, Gregory Sell, Tom Ko, Lukáš Burget and Arnab Ghoshal. Their work appears in journals such as Computer Speech & Language, IEEE/ACM Transactions on Audio Speech and Language Processing, IEEE Transactions on Audio Speech and Language Processing, IEEE Signal Processing Letters and IEEE Transactions on Speech and Audio Processing.
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.