◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Yu Zhang

1 paper hereh-index 11437 citations17 works total

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

author position
  • middle author1

Across the 1 of 1 paper where every author was matched, so the position is known.

fields
  • cs.CL1
same name
  • Yu Zhang — 91 papers, h 38
  • Yu Zhang — 52 papers, h 51
  • Yu Zhang — 28 papers
  • Yu Zhang — 21 papers, h 18
  • Yu Zhang — 20 papers, h 5
  • Yu Zhang — 19 papers, h 27

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

most citedJOIST: A Joint Speech and Text Streaming Model For ASR

1 citations · 1 across the 1 of their papers we have counts for

collaborators
Showing cs.CLShow all

4 papers · 1 filter

cs.CL2023

How to Estimate Model Transferability of Pre-Trained Speech Models?

Zih-Ching Chen, Chao-Han Huck Yang, Bo Li +6

In this work, we introduce a "score-based assessment" framework for estimating the transferability of pre-trained speech models (PSMs) for fine-tuning target tasks. We leverage upo…

cs.CL2023

Mixture-of-Expert Conformer for Streaming Multilingual ASR

Ke Hu, Bo Li, Tara N. Sainath +2

End-to-end models with large capacity have significantly improved multilingual automatic speech recognition, but their computation cost poses challenges for on-device applications.…

cs.CL2023

Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference

Tao Lei, Junwen Bai, Siddhartha Brahma +9

We propose Conditional Adapter (CoDA), a parameter-efficient transfer learning method that also improves inference efficiency. CoDA generalizes beyond standard adapter approaches t…

cs.CL2022★ 1 cited

JOIST: A Joint Speech and Text Streaming Model For ASR

Tara N. Sainath, Rohit Prabhavalkar, Ankur Bapna +6

We present JOIST, an algorithm to train a streaming, cascaded, encoder end-to-end (E2E) model with both speech-text paired inputs, and text-only unpaired inputs. Unlike previous wo…

◍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.