Abstract

Successful sales in today's cutthroat digital marketplace rely not only on quick responses but also on real-time comprehension of consumer intent and emotions. Often emotional cues are ignored by conventional sales tools, due to which it results in lost opportunities and low engagement. To close such gaps in sales, SalesMind offers an AI-powered assistant which gives a score to text and audio conversations, recognizes the emotional states, ansd provides the sales representatives with conversational cues like suggestions and post-call analysis. The system uses VADER, transformer-based models like BERT, and PyTorch-driven speech emotion detection in a hybrid emotion analysis pipeline after recording consumer voice input and converting it to text. Suggestions are customized based on past behaviour and interests using a CRM module supported by MongoDB. Each conversation is given an emotional satisfaction score (0–10), which helps prioritize leads and reflects the customer's mood. The AI driven follow-ups are generally shown to moderate levels of engagement (around 6-7). SalesMind is a responsive real-time sales assistance platform developed using the MERN stack (MongoDB, Express.js, React.js and Node.js) Improved response quality, increased customer interaction, and higher conversion rates are anticipated results, making SalesMind a useful and significant instrument for contemporary sales.

References

• G. Theresa, P. Rajasekaran, and S. Kumar, “Multi-modal emotional analysis in customer relation management and enhancing communication through integrated affective computing,” Scientific Reports, vol. 15, no. 26437, pp. 1–12, 2025.
• G. Gamage, D. De Silva, and D. Alahakoon, “Emotion AWARE: An artificial intelligence framework for adaptable, robust, explainable, and multi-granular emotion analysis,” Journal of Big Data, vol. 11, no. 93, pp. 1–18, 2024.
• R. Spain, W. Min, V. Kumaran, J. Pande, and J. Saville, “Applying large language models to enhance dialogue and communication analysis for adaptive team training,” International Journal of Artificial Intelligence in Education, 2025.
• N. Rane, M. Paramesha, and S. Choudhary, “Artificial intelligence in sales and marketing: Enhancing customer satisfaction, experience and loyalty,” SSRN Electronic Journal, 2024.
• M. Płaza, M. Kozłowski, and R. Kazała, “Emotion recognition method for call/contact centre systems,” Applied Sciences, vol. 12, no. 21, p. 10951, 2022.
• H. Lian, C. Lu, S. Li, Y. Zhao, and Y. Zong, “A survey of deep learning-based multimodal emotion recognition: Speech, text, and face,” Entropy, vol. 25, no. 10, p. 1440, 2023.
• S. Wang and L. Zhou, “Emotion-aware human-computer interaction using VADER and BERT,” IEEE Transactions on Computational Social Systems, vol. 10, no. 3, 2023.
• B. T. Atmaja and A. Sasou, “Sentiment analysis and emotion recognition from speech using universal speech representations,” Sensors, vol. 22, no. 17, p. 6369, 2022.
• M. Khan, S. S. R. Abidi, and A. M. S. Ali, “MemoCMT: Multimodal emotion recognition using cross-modal transformer-based feature fusion,” Scientific Reports, vol. 15, no. 89202, pp. 1–12, 2025.
• F. Di Luzio, “An explainable fast deep neural network for emotion recognition,” Neurocomputing, vol. 456, pp. 1–12, 2025.
• A. Anupama, “Deep learning approach for emotions detection,” E3S Web of Conferences, vol. 36, p. 07007, 2023.
• Z. Lian, “Explainable multimodal emotion recognition,” arXiv preprint arXiv:2306.15401, 2023.
• M. Norval and Z. Wang, “Explainable artificial intelligence techniques for speech emotion recognition: A focus on XAI models,” Inteligencia Artificial, vol. 28, no. 76, pp. 85–123, 2025.
• R. Pereira, “Systematic review of emotion detection with computer vision,” PMC, vol. 11175284, 2024.
• T. Huang, X. Li, and S. Chen, “Real-time emotion detection for call center agents,” Journal of Intelligent Systems, vol. 31, no. 4, pp. 433–446, 2022.
• V. Prasad et al., “Hybrid deep learning for voice emotion analysis,” IEEE Transactions on Affective Computing, 2023.
• P. Das and A. Sengupta, “Multimodal sentiment fusion for real-time CRM,” Expert Systems with Applications, vol. 237, 2024.
• S. Bansal, P. Verma, and L. Singh, “BERT-based contextual emotion understanding in conversational AI,” ACM Transactions on Intelligent Systems, 2023.
• Y. Zhang et al., “Explainable emotion recognition with multimodal attention networks,” Pattern Recognition Letters, vol. 168, pp. 134–142, 2023.
• E. Silva et al., “Ethical emotion AI for business communication,” AI and Ethics Journal, vol. 5, pp. 89–101, 2025.