Laxmi Pandey Research Scientist AI Speech | Meta CV | E-Mail | Google Scholar | Github

I am a Research Scientist at Meta AI, where I work with the Speech team. My research is interdisciplinary, encompassing various fields such as audio-visual speech recognition, natural language processing, human-computer interaction, and applied artificial intelligence. Prior to joining Meta AI, I pursued my doctoral studies as a fellow at the University of California, Merced, under the guidance of Prof. Ahmed Sabbir Arif. During my PhD, my research garnered recognition through several prestigious awards, including the Fred and Mitzie Ruiz Fellowship, the Hatano Cognitive Development Research Fellowship, the ACM-W Scholarship, and the SIGIR Travel Grant. Additionally, I hold a Master's degree from the Indian Institute of Technology Kanpur, India, where I worked with Prof. Rajesh M Hegde. Over the course of my research, my work has been featured in numerous national and international media outlets, resulting in 18 publications.

Publications

MELDER: The Design and Evaluation of a Real-time Silent Speech Recognizer for Mobile Devices
Laxmi Pandey, Ahmed Sabbir Ari
CHI Conference on Human Factors in Computing Systems, CHI 2024

Improving Data Driven Inverse Text Normalization using Data Augmentation
Laxmi Pandey, Debjyoti Paul, Pooja Chitkara, Yutong Pang, Xuedong Zhang, Kjell Schubert, Mark Chou, Shu Liu, Yatharth Saraf
arXiv preprint arXiv:2207.09674, 2022

Design and Evaluation of a Silent Speech-Based Selection Method for Eye-Gaze Pointing
Laxmi Pandey, Ahmed Sabbir Arif
ACM Interactive Surfaces and Spaces Conference, ISS 2022

Effects of Speaking Rate on Speech and Silent Speech Recognition
Laxmi Pandey, Ahmed Sabbir Arif
Extended Abstracts of the 2022 CHI Conference on Human Factors in Computing Systems, CHI EA 2022

Silent Speech and Emotion Recognition from Vocal Tract Shape Dynamics in Real-Time MRI
Laxmi Pandey, Ahmed Sabbir Arif
Special Interest Group on Computer Graphics and Interactive Techniques Conference Posters, SIGGRAPH 2021 [Poster]

LipType: A Silent Speech Recognizer Augmented with an Independent Repair Model
Laxmi Pandey, Ahmed Sabbir Arif
CHI Conference on Human Factors in Computing Systems, CHI 2021

Acceptability of Speech and Silent Speech Input Methods in Private and Public
Laxmi Pandey, Khalad Hasan, Ahmed Sabbir Arif
CHI Conference on Human Factors in Computing Systems, CHI 2021

Enabling Text Translation Using the Suggestion Bar of a Virtual Keyboard
Laxmi Pandey, Ahmed Sabbir Arif
IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020

Enabling Predictive Number Entry and Editing on Touchscreen-Based Mobile Devices
Laxmi Pandey, Ahmed Sabbir Arif
ACM Conference on Human Information Interaction and Retrieval, CHIIR 2020

TiltWriter: Design and Evaluation of a No-touch Tilt-based Text Entry Method for Handheld Devices
Steven J. Castellucci, I. Scott MacKenzie, Mudit Misra, Laxmi Pandey, Ahmed Sabbir Arif
ACM International Conference on Mobile and Ubiquitous Multimedia, MUM 2019

Context-Sensitive App Prediction on the Suggestion Bar of a Mobile Keyboard
Laxmi Pandey, Ahmed Sabbir Arif
ACM International Conference on Mobile and Ubiquitous Multimedia, MUM 2019 [Poster]

Multi-Channel Joint speech dereverberation and denoising using Deep Priors
Aditya Raikar , Saurya Basu, Laxmi Pandey, Rajesh M. Hegde
IEEE India Council International Conference, INDICON 2018

LSTM Based Attentive Fusion of Spectral and Prosodic Information for Keyword Spotting
Laxmi Pandey, Karan Nathwani
Interspeech 2018

Monaural Audio Source Separation Using Variational Autoencoders
Laxmi Pandey, Anurendra Kumar, Vinay Namboodiri
Interspeech 2018

Deep Clean: GPU Powered Speech Denoising using Adversarial Learning
Laxmi Pandey, Nitish Divakar, Krishna D N, Anuroop Iyengar
NVIDIA’s GPU Technology Conference, GTC 2018 [Poster]

Keyword Spotting in Continuous Speech using Spectral and Prosodic Information Fusion
Laxmi Pandey, Rajesh M. Hegde
Circuits Systems and Signal Processing, CSSP Springer, 2018 [Journal]

Fusion of Spectral and Prosodic Information using Combined Error Optimization for Keyword Spotting
Laxmi Pandey, Kuldeep Chaudhary, Rajesh M. Hegde
IEEE National Conference on Communications, NCC 2017

Domain Specific Audio Indexing Using Linguistic Information
L. Pandey, K. Nathwani, S. Kaur, I. Hussain, R. Pathak, G. Singh, S. Tiwari, Rajesh M. Hegde
IEEE Symposium on Signal Processing and Information Technology, ISSPIT 2014

News