Forced Alignment

Forced Alignment is a computational technique in speech recognition that synchronizes a known transcription with a corresponding acoustic speech signal by precisely aligning each phonetic or lexical unit in time, distinguishing itself from other alignment methods through its use of predefined, ground-truth textual sequences to guide the temporal mapping process.

78

Publications

4.3K

Citations

272

Authors

86

Institutions

Publications per year

2017–2026

22

Authors

272

  1. JY
    Jiahong Yuan

    University of Pennsylvania, United States

    5 publications · 230 citations

    5

    h-index

  2. ML
    Mark Liberman

    University of Pennsylvania, United States

    4 publications · 119 citations

    4

    h-index

  3. AK
    Athanasios Katsamanis

    University of Southern California, United States

    2 publications · 178 citations

    2

    h-index

  4. KG
    Kyle Gorman

    Oregon Health & Science University, United States

    2 publications · 339 citations

    2

    h-index

  5. HM
    Helen Meng

    Chinese University of Hong Kong, Hong Kong SAR China

    2 publications · 31 citations

    2

    h-index

1–5 of 272

Venues

  1. 3

    h-index

  2. The Journal of the Acoustical Society of America

    JASA · 2 publications · 79 citations

    2

    h-index

  3. Linguistics Vanguard

    2 publications · 53 citations

    2

    h-index

  4. Applied Physics Letters

    1 publications · 105 citations

    1

    h-index

  5. 1

    h-index

1–5