Sriram Ganapathy

Artificial Intelligence · 2012–2025

A researcher in the Science corpus: 7 papers; trusts 24 researchers and is trusted by 8 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 50 citations into it; #14,760 of 35,345 by trust here, #15,542 by citations
• Signal Processing — 41 citations into it; #2,877 of 7,572 by trust here, #2,400 by citations
• Speech & Audio — 33 citations into it; #495 of 1,076 by trust here, #628 by citations
• Evaluation & Benchmarks — 9 citations into it; #2,989 of 3,147 by trust here, #2,799 by citations
• Natural Language Processing — 7 citations into it
• Representation & Self-Supervised Learning — 7 citations into it
• Computer Vision and Pattern Recognition — 5 citations into it

Whom Sriram Ganapathy trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Hynek Hermansky
2. Daniel Garcia-Romero
3. Florin Curelaru
4. Patrick Kenny
5. David Snyder
6. Daniel Povey
7. Simon J. D. Prince
8. C. Cieri
9. George Saon
10. Geoffrey E. Hinton

Who trusts Sriram Ganapathy overall

1. Pawel Swietojanski
2. Arnab Ghoshal
3. S. Renals
4. Sibo Tong
5. Peter Bell
6. Zolt'an Tuske
7. Samuel Thomas
8. Jui-Ting Huang

Papers from Sriram Ganapathy's perspective

Ordered by how strongly the researchers Sriram Ganapathy trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Long Short-Term Memory
5. The Kaldi Speech Recognition Toolkit
6. Attention is All you Need (Neural Information Processing Systems)
7. Learning Deep Architectures for AI
8. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
9. Gradient-based learning applied to document recognition
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• Multilingual MLP features for low-resource LVCSR systems (2012) — 122 citations
• Increasing the robustness of CNN acoustic models using autoregressive moving average spectrogram features and channel dropout (2017) — 41 citations
• Deep learning methods for unsupervised acoustic modeling — Leap submission to ZeroSpeech challenge 2017 (2017) — 13 citations
• The Second DIHARD Diarization Challenge: Dataset, task, and baselines (2019) — 203 citations
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025) — 3,609 citations
• Coswara - A Database of Breathing, Cough, and Voice Sounds for COVID-19 Diagnosis (2020) — 328 citations
• The IBM 2016 Speaker Recognition System (2016) — 48 citations