activity
20202026
most citedCitrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition

43 citations · 102 across the 48 of their papers we have counts for

collaborators
Showing 2022Show all

2 papers · 1 filter

eess.AS2022★ 4 cited

A Compact End-to-End Model with Local and Global Context for Spoken Language Identification

Fei Jia, Nithin Rao Koluguri, Jagadeesh Balam +1

We introduce TitaNet-LID, a compact end-to-end neural network for Spoken Language Identification (LID) that is based on the ContextNet architecture. TitaNet-LID employs 1D depth-wi…

eess.AS2022★ 4 cited

Multi-scale Speaker Diarization with Dynamic Scale Weighting

Tae Jin Park, Nithin Rao Koluguri, Jagadeesh Balam +1

Speaker diarization systems are challenged by a trade-off between the temporal resolution and the fidelity of the speaker representation. By obtaining a superior temporal resolutio…