Speech emotion recognition (SER) is a fundamental task in affective computing; however, traditional unimodal approaches often struggle to capture the complex emotional cues present in spontaneous conversational speech. Bimodal frameworks that integrate acoustic and textual information have therefore emerged to provide complementary semantic and acoustic representations. This study proposes a bimodal SER framework based on a hybrid convolutional neural network–long short-term memory (CNN–LSTM) architecture. Using the Multimodal EmotionLines Dataset (MELD), the framework combines temporal acoustic features, statistical acoustic features, and predicted textual sentiment. Experimental results indicate that the proposed model achieves reliable recognition of majority emotion classes but exhibits limited performance on underrepresented minority classes due to severe class imbalance. To better understand the contribution of each modality, feature sufficiency and feature necessity analyses were conducted. Furthermore, an evaluation of alternative fusion strategies showed that the expressive attention networks did not provide meaningful performance improvements over simple feature concatenation. These findings suggest that class imbalance, rather than fusion complexity, remains the primary limitation in conversational SER, highlighting the importance of addressing data imbalance before pursuing more sophisticated multimodal architectures.
Storage Location Assignment Problem (SLAP) is a study on how products should be stored in a warehouse space. Although studies have shown that arranging products based on their duration of stay can decrease the stacker crane travel time, this policy requires exact knowledge of the product's duration of stay. To the best of the author's knowledge, most studies on duration-of-stay storage policy (DOS) are on single-deep automated storage/retrieval systems (AS/RS), and hence their viability in double-deep AS/RS has not yet been extensively studied. To close this literature gap, this paper aims to study the performance of DOS on double-deep AS/RS in third-party logistics (3PL) warehouses. The study starts by building a simulation model of a double-deep automated warehouse. Based on the warehouse model, simulations using three different policies: random storage policy (RAN), closest-open-location storage policy (COL) and DOS are performed. To evaluate the effectiveness of the storage policies, the average dual-command-cycle (DCC) travel time for each operation is compared under varying warehouse conditions. The results indicate that the duration-of-stay (DOS) storage policy consistently outperforms both random (RAN) and closest-open-location (COL) policies in reducing travel time and mitigating blockage. This demonstrates the importance of incorporating expected retrieval behaviour into storage location assignment decisions.
Song-Yi Ng, Lee-Yeng Ong, M. Leow· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
