the open
    research
    Contribute
    Back to the reading lists

    Language, speech & LLMs· 2006

    Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks

    Alex Graves (first author) · 2006

    Read the original

    DOI 10.1145/1143844.1143891OpenAlex W7027429494

    On the reading lists

    Why it matters

    Introduced CTC, enabling end-to-end sequence recognition without manually aligned training labels.

    Condensed from the expert lists' notes.

    The record

    First released
    2006 (from OpenAlex)
    Citations
    5,370 citations, as counted by OpenAlex (CC0)
    Named by
    both expert lists
    Score
    0.583 · computed rank 167 · consensus 0.98, must-read 1, citations percentile 0.538 (2000s · language), awards 0, existing lists 0. Method

    Editor's notes

    • Readability check: pass: CTC: a lasting loss for sequence labelling. (AI draft (Claude), not yet reviewed, 2026-10-29)

    Data sources

    Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.