Description

Owing to the suprasegmental behavior of emotional speech, turn-level features have demonstrated a better success than frame-level features for recognition-related tasks. Conventionally, such features are obtained via a brute-force collection

Owing to the suprasegmental behavior of emotional speech, turn-level features have demonstrated a better success than frame-level features for recognition-related tasks. Conventionally, such features are obtained via a brute-force collection of statistics over frames, thereby losing important local information in the process which affects the performance. To overcome these limitations, a novel feature extraction approach using latent topic models (LTMs) is presented in this study.

Reuse Permissions
  • application/pdf

    Download count: 0

    Details

    Contributors
    Date Created
    • 2015-01-25
    Resource Type
  • Text
  • Collections this item is in
    Identifier
    • Digital object identifier: 10.1186/s13636-014-0049-y
    • Identifier Type
      International standard serial number
      Identifier Value
      1687-4714
    • Identifier Type
      International standard serial number
      Identifier Value
      1687-4722

    Citation and reuse

    Cite this item

    This is a suggested citation. Consult the appropriate style guide for specific citation guidelines.

    Shah, Mohit, Chakrabarti, Chaitali, & Spanias, Andreas (2015). Within and cross-corpus speech emotion recognition using latent topic model-based features. EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING, 2015:4. http://dx.doi.org/10.1186/s13636-014-0049-y

    Machine-readable links