◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Ehsan Variani

17 papers hereh-index 152.2k citations43 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author5
  • middle author11
  • last author1

Across the 17 of 17 papers where every author was matched, so the position is known.

fields
  • eess.AS6
  • cs.CL4
  • cs.SD3
  • cs.LG2
  • cs.CV1
  • cs.IT1

identity via Semantic Scholar / OpenAlex

activity
20152026
most citedGlobal Normalization for Streaming Speech Recognition in a Modular Framework

6 citations · 7 across the 12 of their papers we have counts for

collaborators
Showing 2022 · cs.LGShow all

1 paper · 2 filters

cs.LG2022★ 6 cited

Global Normalization for Streaming Speech Recognition in a Modular Framework

Ehsan Variani, Ke Wu, Michael Riley +3

We introduce the Globally Normalized Autoregressive Transducer (GNAT) for addressing the label bias problem in streaming speech recognition. Our solution admits a tractable exact c…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.