the open
    research
    Contribute
    Back to the reading lists

    Language, speech & LLMs· 2018

    Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation

    Yi Luo (first author) · 2018 · published 2019

    Read the original

    DOI 10.1109/taslp.2019.2915167arXiv 1809.07454OpenAlex W2952218014

    On the reading lists

    Why it matters

    Established high-performance end-to-end time-domain separation, surpassing traditional spectrogram masking.

    Condensed from the expert lists' notes.

    The record

    First released
    2018 (from arXiv 1809.07454)
    Published
    2019
    Citations
    2,281 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.360 · computed rank 453 · consensus 0.68, must-read 0, citations percentile 0.444 (2010s · language), awards 0, existing lists 0. Method

    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.