TY - GEN
T1 - Dysfluency Classification in Speech Using a Biological Sound Perception Model
AU - Jouaiti, Melanie
AU - Dautenhahn, Kerstin
N1 - Presented 27 Nov 2022 at the 9th International Conference on Soft Computing & Machine Intelligence (ISCMI)
PY - 2023/3/21
Y1 - 2023/3/21
N2 - Dysfluency classification for stuttered speech has been tackled from different perspectives over the years, with research being more and more focused on deep learning. Here, we use a specific biological model of sound texture perception to extract a subband representation of speech and statistical features. A statistical analysis was also performed to identify relevant features. Afterwards, dysfluency classification was performed using a Random Forest Classifier to perform multi-label classification on the FluencyBank dataset and Support Vector Machine on the UCLASS dataset. This method performs as well or better than current state of the art deep learning algorithm, suggesting that approaching speech classification problems from a more biological point of view is a promising direction.
AB - Dysfluency classification for stuttered speech has been tackled from different perspectives over the years, with research being more and more focused on deep learning. Here, we use a specific biological model of sound texture perception to extract a subband representation of speech and statistical features. A statistical analysis was also performed to identify relevant features. Afterwards, dysfluency classification was performed using a Random Forest Classifier to perform multi-label classification on the FluencyBank dataset and Support Vector Machine on the UCLASS dataset. This method performs as well or better than current state of the art deep learning algorithm, suggesting that approaching speech classification problems from a more biological point of view is a promising direction.
KW - Support vector machines
KW - Deep learning
KW - Statistical analysis
KW - Biological system modeling
KW - Computational modeling
KW - Feature extraction
KW - Real-time systems
U2 - 10.1109/ISCMI56532.2022.10068490
DO - 10.1109/ISCMI56532.2022.10068490
M3 - Conference contribution
SN - 9798350320893
T3 - International Conference on Soft Computing and Machine Intelligence (ISCMI)
SP - 173
EP - 177
BT - 2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI)
PB - IEEE
T2 - 2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI)
Y2 - 26 November 2022 through 27 November 2022
ER -