activity
20182022
most citedSynt++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition

4 citations · 5 across the 6 of their papers we have counts for

collaborators

9 papers

cs.CV2022

I see what you hear: a vision-inspired method to localize words

Mohammad Samragh, Arnav Kundu, Ting-Yao Hu +5

This paper explores the possibility of using visual object detection techniques for word localization in speech data. Object detection has been thoroughly studied in the contempora…

eess.AS20214 cited

Synt++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition

Ting-Yao Hu, Mohammadreza Armandpour, Ashish Shrivastava +3

With recent advances in speech synthesis, synthetic data is becoming a viable alternative to real data for training speech recognition models. However, machine learning with synthe…

cs.AR2021

SLAP: A Split Latency Adaptive VLIW pipeline architecture which enables on-the-fly variable SIMD vector-length

Ashish Shrivastava, Alan Gatherer, Tong Sun +2

Over the last decade the relative latency of access to shared memory by multicore increased as wire resistance dominated latency and low wire density layout pushed multiport memori…

cs.AR2020

Towards a Domain Specific Solution for a New Generation of Wireless Modems

Alan Gatherer, Ashish Shrivastava, Hao Luan +3

Wireless cellular System on Chip (SoC) are experiencing unprecedented demands on data rate, latency use case variety. 5G wireless technologies require a massive number of antennas…

cs.CL2020

Saying No is An Art: Contextualized Fallback Responses for Unanswerable Dialogue Queries

Ashish Shrivastava, Kaustubh Dhole, Abhinav Bhatt +1

Despite end-to-end neural systems making significant progress in the last decade for task-oriented as well as chit-chat based dialogue systems, most dialogue systems rely on hybrid…

cs.LG20201 cited

SapAugment: Learning A Sample Adaptive Policy for Data Augmentation

Ting-Yao Hu, Ashish Shrivastava, Jen-Hao Rick Chang +5

Data augmentation methods usually apply the same augmentation (or a mix of them) to all the training samples. For example, to perturb data with noise, the noise is sampled from a N…