Saurabh Adya

Orcid: 0009-0000-4533-6577

According to our database1, Saurabh Adya authored at least 18 papers between 2018 and 2024.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Multimodal Large Language Models with Fusion Low Rank Adaptation for Device Directed Speech Detection.
CoRR, 2024

Comparative Analysis of Personalized Voice Activity Detection Systems: Assessing Real-World Effectiveness.
CoRR, 2024

eDKM: An Efficient and Accurate Train-Time Weight Clustering for Large Language Models.
IEEE Comput. Archit. Lett., 2024

Streaming Anchor Loss: Augmenting Supervision with Temporal Significance.
Proceedings of the IEEE International Conference on Acoustics, 2024

Modality Drop-Out for Multimodal Device Directed Speech Detection Using Verbal and Non-Verbal Features.
Proceedings of the IEEE International Conference on Acoustics, 2024

2023
Modality Dropout for Multimodal Device Directed Speech Detection using Verbal and Non-Verbal Features.
CoRR, 2023

R^2: Range Regularization for Model Compression and Quantization.
CoRR, 2023

PDP: Parameter-free Differentiable Pruning is All You Need.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Efficient Multimodal Neural Networks for Trigger-less Voice Assistants.
Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

Less Is More: A Unified Architecture for Device-Directed Speech Detection with Multiple Invocation Types.
Proceedings of the IEEE International Conference on Acoustics, 2023

2022
Improving Voice Trigger Detection with Metric Learning.
Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

Device-Directed Speech Detection: Regularization via Distillation for Weakly-Supervised Models.
Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

DKM: Differentiable k-Means Clustering Layer for Neural Network Compression.
Proceedings of the Tenth International Conference on Learning Representations, 2022

2021
Streaming Transformer for Hardware Efficient Voice Trigger Detection and False Trigger Mitigation.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

2020
Hybrid Transformer/CTC Networks for Hardware Efficient Voice Triggering.
Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

Lattice-Based Improvements for Voice Triggering Using Graph Neural Networks.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2018
Nonlinear Conjugate Gradients For Scaling Synchronous Distributed DNN Training.
CoRR, 2018

Democratizing Production-Scale Distributed Deep Learning.
CoRR, 2018


  Loading...