CV

Download here

Education

• B.Tech. in Electronics and Communication Engineering, Indian Institute of Technology Guwahati, 2015
• Currently Ph.D. student (2016) in Computer Science and Engineering, The Ohio State University

Work experience

• Summer 2021: Research Internship
  • Facebook Reality Labs
  • Facebook Inc.
  • Worked on end-to-end multichannel speech enhnacement
• Summer 2020: Research Internship
  • Video ASR
  • Facebook Inc.
  • Worked on speech enhancement for robust automatic speech recognition
• Summer 2019: Research Internship
  • Siri Understanding
  • Apple Inc.
  • Worked on acoustic modeling for automatic speech recognition
• Summer 2015 to Summer 2016: Research Engineer
  • Aspiring Minds Assessments Private Limited
• Summer 2014: Research Intern
  • University of Alberta
  • Supervisor: Jie Han
• Summer 2013: Research Intern
  • Cvest-IIIT Hyderabad
  • Supervisor: Shubhajit Roy Chowdhury

Awards

• Presidential Fellowship, 2021
  • The Ohio State University

Publications

Attentive Recurrent Network for Low-Latency Active Noise Control

H. Zhang, A. Pandey and D. L. Wang, "Attentive Recurrent Network for Low-Latency Active Noise Control," in proceedings of INTERSPEECH, 2022, pp. 956-960.

Attentive Training: A New Training Framework for Talker-independent Speaker Extraction

A. Pandey and D. L. Wang, "Attentive Training: A New Training Framework for Talker-independent Speaker Extraction," in proceedings of INTERSPEECH, 2022, pp. 201-205.

Time-domain Ad-hoc Array Speech Enhancement Using a Triple-path Network

A. Pandey, B. Xu, A. Kumar, J. Donley, P. Calamia, and D. L. Wang, "Time-domain Ad-hoc Array Speech Enhancement Using a Triple-path Network," in proceedings of INTERSPEECH, 2022, pp. 729-733.

Multichannel Speech Enhancement Without Beamforming

A. Pandey, B. Xu, A. Kumar, J. Donley, P.Calamia, and D. L. Wang, "Multichannel Speech Enhancement Without Beamforming," in proceedings of ICASSP, 2022, pp. 6502-6506.

TPARN: Triple-Path Attentive Recurrent Network for Time-Domain Multichannel Speech Enhancement

A. Pandey, B. Xu, A. Kumar, J. Donley, P.Calamia, and D. L. Wang, "TPARN: Triple-Path Attentive Recurrent Network for Time-Domain Multichannel Speech Enhancement," in proceedings of ICASSP, 2022, pp. 6497-6501.

Self-attending RNN for Speech Enhancement to Improve Cross-corpus Generalization

A. Pandey and D. L. Wang, "Self-attending RNN for Speech Enhancement to Improve Cross-corpus Generalization," in IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 30, pp. 1374-1385, 2022.

Dense CNN with Self-Attention for Time-Domain Speech Enhancement

A. Pandey and D. L. Wang, "Dense CNN with Self-Attention for Time-Domain Speech Enhancement," in IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 29, pp. 1270-1279, 2021.

Dual Application of Speech Enhancement for Automatic Speech Recognition

A. Pandey, C. Liu, Y. Wang and Y. Saraf, "Dual Application of Speech Enhancement for Automatic Speech Recognition," in Workshop on Spoken Language Technology, 2021, pp. 223-228.

Dual-path Self-Attention RNN for Real-Time Speech Enhancement

A. Pandey and D. L. Wang, "Dual-path Self-Attention RNN for Real-Time Speech Enhancement," arXiv:2010.12713, 2020.

On Cross-Corpus Generalization of Deep Learning Based Speech Enhancement

A. Pandey and D. L. Wang, "On Cross-Corpus Generalization of Deep Learning Based Speech Enhancement," in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 28, pp. 2489-2499, 2020.

Learning Complex Spectral Mapping for Speech Enhancement with Improved Cross-corpus Generalization

A. Pandey and D. L. Wang, "Learning Complex Spectral Mapping for Speech Enhancement with Improved Cross-Corpus Generalization,", in proceedings of INTERSPEECH, 2020, pp. 4511-4515.

Densely Connected Neural Network with Dilated Convolutions for Real-Time Speech Enhancement in the Time Domain

A. Pandey and D. L. Wang, "Densely Connected Neural Network with Dilated Convolutions for Real-Time Speech Enhancement in the Time Domain,", in proceedings of ICASSP, 2020, pp. 6629-6633.

A New Framework for CNN Based Speech Enhancement in the Time Domain

A. Pandey and D. L. Wang, "A New Framework for CNN-Based Speech Enhancement in the Time Domain," in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 27, pp. 1179-1188, 2019.

Exploring Deep Complex Networks for Complex Spectrogram Enhancement

A. Pandey and D. L. Wang, "Exploring Deep Complex Networks for Complex Spectrogram Enhancement," in proceedings of ICASSP, 2019, pp. 6885-6889.

TCNN: Temporal Convolutional Neural Network for Real-Time Speech Enhancement in the Time Domain

A. Pandey and D. L. Wang, "TCNN: Temporal Convolutional Neural Network for Real-time Speech Enhancement in the Time Domain," in proceedings of ICASSP, 2019, pp. 6875-6879.

A New Framework for Supervised Speech Enhancement in the Time Domain

A. Pandey and D. L. Wang, "A New Framework for Supervised Speech Enhancement in the Time Domain," in proceedings of INTERSPEECH, 2018, pp. 1136-1140.

On Adversarial Training and Loss Functions for Speech Enhancement

A. Pandey and D. L. Wang, "On Adversarial Training and Loss Functions for Speech Enhancement", in proceedings of ICASSP, 2018, pp. 5414-5418.

Significance of Glottal Activity Detection for Speaker Verification in Degraded and Limited Data Condition

A. Pandey, R. K. Das, N. Adiga, N. Gupta and S. R. M. Prasanna, "Significance of Glottal Activity Detection for Speaker Verification in Degraded and Limited Data Condition," in proceedings of TENCON, 2015, pp. 1-6.