TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/SyncVSR

SyncVSR

Reported on 8 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision7 results

  • LipreadingonLRS2
    Word Error Rate (WER)· uses extra data· 2024-06-18
    16.5
    best: 14.6 (Auto-AVSR)
    SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token SynchronizationarXiv:2406.12233
  • LipreadingonLRS2
    Word Error Rate (WER)· 2024-06-18
    28.9
    best: 14.6 (Auto-AVSR)
    SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token SynchronizationarXiv:2406.12233
  • LipreadingonLip Reading in the Wild
    Top-1 Accuracy· 2024-06-18
    93.2
    best: 95 (SyncVSR (Word Boundary))
    SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token SynchronizationarXiv:2406.12233
  • LipreadingonLRS3-TED
    Word Error Rate (WER)· uses extra data· 2024-06-18
    21.5
    best: 12.8 (LP + Conformer)
    SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token SynchronizationarXiv:2406.12233
  • LipreadingonLRS3-TED
    Word Error Rate (WER)· 2024-06-18
    31.2
    best: 12.8 (LP + Conformer)
    SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token SynchronizationarXiv:2406.12233
  • LipreadingonLRW
    Top 1 Accuracy· 2024-06-18
    75.1
    best: 80.3 (SyncVSR (Word Boundary))
    SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token SynchronizationarXiv:2406.12233
  • LipreadingonLRS2
    Word Error Rate (WER)· 2024-06-18
    74.6
    best: 14.6 (Auto-AVSR)
    SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token SynchronizationarXiv:2406.12233

Natural Language Processing7 results

  • Natural Language TransductiononLRS2
    Word Error Rate (WER)· uses extra data· 2024-06-18
    16.5
    best: 14.6 (Auto-AVSR)
    SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token SynchronizationarXiv:2406.12233
  • Natural Language TransductiononLRS2
    Word Error Rate (WER)· 2024-06-18
    28.9
    best: 14.6 (Auto-AVSR)
    SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token SynchronizationarXiv:2406.12233
  • Natural Language TransductiononLip Reading in the Wild
    Top-1 Accuracy· 2024-06-18
    93.2
    best: 95 (SyncVSR (Word Boundary))
    SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token SynchronizationarXiv:2406.12233
  • Natural Language TransductiononLRS3-TED
    Word Error Rate (WER)· uses extra data· 2024-06-18
    21.5
    best: 12.8 (LP + Conformer)
    SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token SynchronizationarXiv:2406.12233
  • Natural Language TransductiononLRS3-TED
    Word Error Rate (WER)· 2024-06-18
    31.2
    best: 12.8 (LP + Conformer)
    SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token SynchronizationarXiv:2406.12233
  • Natural Language TransductiononLRW
    Top 1 Accuracy· 2024-06-18
    75.1
    best: 80.3 (SyncVSR (Word Boundary))
    SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token SynchronizationarXiv:2406.12233
  • Natural Language TransductiononLRS2
    Word Error Rate (WER)· 2024-06-18
    74.6
    best: 14.6 (Auto-AVSR)
    SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token SynchronizationarXiv:2406.12233