Vocal effort compensation for MFCC feature extraction in a shouted versus normal speaker recognition task

Emma Jokinen*, Rahim Saeidi, Tomi Kinnunen, Paavo Alku

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

12 Citations (Scopus)
3 Downloads (Pure)


In shouting, speakers use increased vocal effort to convey spoken messages over distance or above environmental noise. For automatic speaker recognition systems trained using normal speech, shouting causes a severe vocal effort mismatch between the enrollment and test hence reducing the recognition performance. In this study, two compensation methods are proposed to tackle the mismatch in a shouted versus normal speaker recognition task. These techniques are applied in the feature extraction stage of a speaker recognition system to modify the spectral envelopes of shouts to be closer to those in normal speech. The techniques modify the all-pole power spectrum of the MFCC computation chain with shouted-to-normal compensation filtering that is obtained using a GMM-based statistical mapping. In an evaluation using the state-of-the-art i-vector based recognition system, the proposed techniques provided considerable improvements in identification rates compared to the case when shouted speech spectra were not processed.

Original languageEnglish
Pages (from-to)1-11
Number of pages11
JournalComputer Speech and Language
Publication statusPublished - 1 Jan 2019
MoE publication typeA1 Journal article-refereed


  • Shouted speech
  • Speaker recognition
  • Vocal effort mismatch

Fingerprint Dive into the research topics of 'Vocal effort compensation for MFCC feature extraction in a shouted versus normal speaker recognition task'. Together they form a unique fingerprint.

  • Projects

    Interdisciplinary research on statistical parametric speech synthesis

    Juvela, L., Airaksinen, M., Bollepalli, B., Bäckström, T., Pohjalainen, J., Kakouros, S., Gowda, D., Jokinen, E. & Alku, P.


    Project: Academy of Finland: Other research funding



    Mikko Hakala (Manager)

    School of Science

    Facility/equipment: Facility

  • Cite this