Unit Selection Synthesis

Unit Selection Synthesis is a speech synthesis method that concatenates pre-recorded acoustic units selected from a large speech database to generate natural-sounding utterances by optimizing for prosodic and contextual continuity.

168

Publications

7.6K

Citations

405

Authors

109

Institutions

Publications per year

2017–2026

8

Variants

Unit Selection Speech Synthesis

Authors

405

  1. AW
    Alan W. Black

    Carnegie Mellon University, United States

    19 publications · 2.6K citations

    16

    h-index

  2. SK
    Simon King

    University of Edinburgh, United Kingdom

    17 publications · 639 citations

    13

    h-index

  3. RA
    Robert A. Clark

    The University of Texas at San Antonio Health Science Center, United States

    9 publications · 387 citations

    9

    h-index

  4. HZ
    Heiga Zen

    Nagoya Institute of Technology, Japan

    8 publications · 2.1K citations

    8

    h-index

  5. AK
    Ann K. Syrdal

    AT&T (United States), United States

    7 publications · 444 citations

    7

    h-index

1–5 of 405

Venues

  1. 5

    h-index

  2. Speech Communication

    5 publications · 1.5K citations

    5

    h-index

  3. 4

    h-index

  4. SSW

    3 publications · 73 citations

    3

    h-index

  5. IEICE Transactions on Information and Systems

    3 publications · 63 citations

    3

    h-index

1–5