Automatic Speech Emotion Recognition (SER) plays a vital role in making human–computer interactions more natural and effective. A significant challenge in SER development is the limited availability of diverse emotional speech datasets, which hinders the application of advanced deep learning models. Transfer learning is a machine learning technique that helps address this issue by utilizing knowledge from pre-trained models to improve performance on a new task in a target domain, even with limited data. This study investigates the use of transfer learning from various pre-trained networks, including speaker embedding models such as d-vector, x-vector, and r-vector, and image classification models like AlexNet, GoogLeNet, SqueezeNet, ResNet-18, and ResNet-50. We also propose enhanced versions of the x-vector and r-vector models incorporating Multi-Head Attention Pooling and Angular Margin Softmax, alongside other architectural improvements. Additionally, reverberation from the Room Impulse Response datasets was added to the speech utterances to diversify and augment the available data. Notably, the enhanced r-vector model achieved classification accuracies of 74.05% Unweighted Accuracy (UA) and 73.68% Weighted Accuracy (WA) on the IEMOCAP dataset, and 80.25% UA and 79.81% WA on the CREMA-D dataset, outperforming the existing state-of-the-art methods. This study shows that using cross-domain transfer learning is beneficial for low-resource emotion recognition. The enhanced models developed in other domains (for non-emotional tasks) can further improve the accuracy of SER.

In this article, we present a concert hall of The Fatra House of Arts in Zilina Slovakia, describe the hall itself and examine the acoustical quality of the hall. The concert hall primarily serves for symphony, chamber orchestra and soloist but hosts various cultural and social events as well. The hall is being considered as acoustically exquisite space by many professional musicians and conductors all around the world for a long time. However, real measurement of the objective acoustical quality parameters, that could confirm the subjective assessment, has never been carried out. We conducted the acoustic measurements following the ISO 3382 standard, which specifies methods for evaluating room acoustics using impulse response analysis. The measurements were performed using an omnidirectional sound source and an omnidirectional microphone to capture the room’s impulse responses at multiple receiver positions. From these responses, we assessed reverberation-based (reverberation time, early decay time), energy-based (clarity), spectral-based (bass ratio, treble ratio), and spatial impression-based (lateral energy fraction) objective criteria. The measured results of these parameters demonstrate a correlation with the recommended values found in specialized literature for chamber orchestra performances, with a reverberation time of 2 s, an early decay time of 1.57 s, a clarity of 0.8 dB, and an initial time delay gap of 12 ms.