Benefits of pre-trained mono- and cross-lingual speech representations for spoken language understanding of Dutch dysarthric speech

EURASIP Journal on Audio, Speech, and Music Processing

Table 6 Number of parameters in the SLU models

Model	Encoder	Intent decoder	Total
TDNN-Capsule	19M	737.2K	19.7M
Transformer-Capsule	27M	746.5K	27.7M
TDNN-LSTM	19M	432.7K	19.4M
Transformer-LSTM	27M	531.0K	27.5M