Analysis of constant-Q filterbank based representations for speech emotion recognition - Inria - Institut national de recherche en sciences et technologies du numérique
Journal Articles Digital Signal Processing Year : 2022

Analysis of constant-Q filterbank based representations for speech emotion recognition

Premjeet Singh
  • Function : Author
  • PersonId : 1090407
Shefali Waldekar
  • Function : Author
  • PersonId : 1148674
Goutam Saha
  • Function : Author
  • PersonId : 1090408

Abstract

This work analyzes the constant-Q filterbank-based time-frequency representations for speech emotion recognition (SER). Constant-Q filterbank provides non-linear spectrotemporal representation with higher frequency resolution at low frequencies. Our investigation reveals how the increased low-frequency resolution benefits SER. The time-domain comparative analysis between short-term mel-frequency spectral coefficients (MFSCs) and constant-Q filterbank-based features, namely constant-Q transform (CQT) and continuous wavelet transform (CWT), reveals that constant-Q representations provide higher time-invariance at low-frequencies. This provides increased robustness against emotion irrelevant temporal variations in pitch, especially for low-arousal emotions. The corresponding frequency-domain analysis over different emotion classes shows better resolution of pitch harmonics in constant-Q-based time-frequency representations than MFSC. These advantages of constant-Q representations are further consolidated by SER performance in the extensive evaluation of features over four publicly available databases with six advanced deep neural network architectures as the back-end classifiers. Our inferences in this study hint toward the suitability and potentiality of constant-Q features for SER.
Fichier principal
Vignette du fichier
DSP_Premjeet_Hal.pdf (1.97 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03846173 , version 1 (10-11-2022)

Identifiers

Cite

Premjeet Singh, Shefali Waldekar, Md Sahidullah, Goutam Saha. Analysis of constant-Q filterbank based representations for speech emotion recognition. Digital Signal Processing, 2022, 130, pp.103712. ⟨10.1016/j.dsp.2022.103712⟩. ⟨hal-03846173⟩
30 View
267 Download

Altmetric

Share

More