Table 3.
Computational methods for the feature-extraction phase.
| Method | No. of Studies |
Ref. |
|---|---|---|
| Mel frequency cepstral coefficient (MFCC) | 6 | Sheikh et al., 2023 [6] Manjula et al., 2019 [16] Sheikh et al., 2021 [22] Jouaiti and Dautenhahn, 2022 [23] Sheikh et al., 2022 [25] Filipowicz and Kostek, 2023 [27] |
| Weighted MFCC (WMFCC) | 1 | Gupta et al., 2020 [21] |
| Spectrograms | 3 | Kourkounakis et al., 2020 [20] Al-Banna et al., 2022 [24] Prabhu and Seliya, 2022 [26] |
| Phonation features | 1 | Pravin and Palanivelan, 2021 [17] |
| Ngram | 1 | Alharbi et al., 2020 [19] |
| Character-based features | 1 | Alharbi et al., 2020 [19] |
| Utterance-based features | 1 | Alharbi et al., 2020 [19] |
| Acoustic analysis of voice recordings | 1 | Asci et al., 2023 [18] |
| Word distance features | 1 | Alharbi et al., 2020 [19] |
| Phoneme features | 2 | Sheikh et al., 2023 [6] Sheikh et al., 2022 [25] |
| Squeeze-and-excitation (SE) residual networks | 1 | Kourkounakis et al., 2021 [14] |
| Bidirectional long short-term memory (BLSTM) layers | 1 | Kourkounakis et al., 2021 [14] |
| Speaker embeddings from the ECAPA-TDNN model | 1 | Sheikh et al., 2022 [25] |
| Contextual embeddings from the Wav2Vec2.0 model | 1 | Sheikh et al., 2022 [25] |
| Pitch-determining feature | 1 | Filipowicz and Kostek, 2023 [27] |
| Two-dimensional speech representations | 1 | Filipowicz and Kostek, 2023 [27] |