International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | AI-Enabled Conversational IVR System Using Generative AI for Intelligent Customer Interaction |
|---|---|
| ABSTRACT | A Conversational IVR (CI-IVR) system designed to improve traditional telephony customer service by enabling more natural, personalized automated voice interactions. Key features include integration of large language models, multilingual transformer-based natural language understanding, and neural speech synthesis. The system is cloud-native and modular, with components for noise-robust speech recognition, intent classification, generative response synthesis, sentiment analysis, text-to-speech, and omnichannel dispatch. In tests involving 5,000 calls and simulated 18,400 call interactions, the system achieved 94.7% intent detection accuracy, 870 ms average latency, and more than doubled call containment compared to traditional DTMF systems. It also succeeded in 88.2% of multilingual queries with code-switching across six Indian languages. Overall, the CI-IVR framework presents a robust, scalable, and linguistically adaptive solution for next-generation automated contact center services. If you want, I can help summarize, explain specific parts, or assist with related tasks. |
| AUTHOR | MANJULA P, SANTHOSH MR, SHREYA N GOWDA, SMRUTI S, SUHA NOORAIN HI Assistant Professor,Department of Computer Science and Engineering, Jain Institute of Technology, Davangere, Karnataka, India Department of Computer Science and Engineering, Jain Institute of Technology, Davangere, Karnataka, India |
| VOLUME | 183 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1404113 |
| pdf/113_AI-Enabled Conversational IVR System Using Generative AI for Intelligent Customer Interaction.pdf | |
| KEYWORDS | |
| References | [1] Gartner Research, "Customer Experience in Contact Centers: IVR Abandonment and Business Impact," Gartner Inc., Stamford, CT, Tech. Rep. G00754231, 2022. [Online]. Available: https://www.gartner.com [2] A. Kapoor and R. Mehta, "From DTMF to Conversational AI: A Survey of IVR System Evolution," in Proc. Int. Conf. on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), Tirunelveli, India, 2021, pp. 912–917. doi: 10.1109/ICICV50876.2021.9388361. [3] S. Ramachandran, P. Narayanan, and V. Krishnan, "AI-Powered Intent Classification for Call Deflection in Telecommunications IVR," in Proc. IEEE Region 10 Symp. (TENSYMP), Mumbai, India, 2022, pp. 1–5. doi: 10.1109/TENSYMP54529.2022.9864407. [4] X. Huang and W. Chen, "Spoken Language Understanding for Call Center IVR Using Bidirectional LSTM," in Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2020, pp. 8004–8008. doi: 10.1109/ICASSP40776.2020.9053057. [5] R. Venkataraman and T. Pillai, "AI-Augmented IVR for Retail Banking: Deployment and Operational Outcomes," in Proc. Int. Conf. on Electronics, Information, and Communication (ICEIC), Jeju, Korea, 2023, pp. 1–6. [6] Y. Liu, Z. Zhang, and H. Wang, "Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning," in Proc. Conf. on Empirical Methods in Natural Language Processing (EMNLP), Punta Cana, Dominican Republic, 2021, pp. 1906–1912. doi: 10.18653/v1/2021.emnlp-main.144. [7] P. Sharma and M. Desai, "Intelligent IVR for Tertiary Healthcare: Triage, Scheduling, and Medication Management," Int. J. Med. Inform., vol. 163, Art. no. 104782, 2022. doi: 10.1016/j.ijmedinf.2022.104782. [8] D. Jurafsky and J. H. Martin, Speech and Language Processing, 3rd ed. (draft), Stanford University, 2023. [Online]. Available: https://web.stanford.edu/~jurafsky/slp3/ [9] O. Vinyals and Q. V. Le, "A Neural Conversational Model," arXiv:1506.05869, 2015. [10] D. Yu and L. Deng, Automatic Speech Recognition: A Deep Learning Approach, 2nd ed. Springer, London, UK, 2022. doi: 10.1007/978-1-4471-5779-3. [11] J. Deriu et al., "Survey on Evaluation Methods for Dialogue Systems," Artif. Intell. Rev., vol. 54, no. 1, pp. 755–810, Feb. 2021. doi: 10.1007/s10462-020-09866-x. [12] A. Conneau et al., "Unsupervised Cross-lingual Representation Learning at Scale," in Proc. 58th Annual Meeting of the ACL, Online, 2020, pp. 8440–8451. doi: 10.18653/v1/2020.acl-main.747. [13] M. El Ayadi, M. S. Kamel, and F. Karray, "Survey on Speech Emotion Recognition: Features, Classification Schemes, and Databases," Pattern Recognit., vol. 44, no. 3, pp. 572–587, Mar. 2011. doi: 10.1016/j.patcog.2010.09.020. [14] M. Jiang, L. Chen, and R. Xu, "Latency Optimization for Production Conversational AI via Speculative Decoding and Streaming Synthesis," in Proc. Int. Conf. on Artificial Intelligence and Speech Technology (AIST), New Delhi, India, 2023, pp. 1–7. [15] T. Brown et al., "Language Models are Few-Shot Learners," in Proc. NeurIPS, vol. 33, 2020, pp. 1877–1901. [16] A. Radford et al., "Robust Speech Recognition via Large-Scale Weak Supervision," in Proc. ICML, Honolulu, HI, 2023, pp. 28492–28518. [17] E. J. Hu et al., "LoRA: Low-Rank Adaptation of Large Language Models," in Proc. ICLR, Virtual, 2022. arXiv:2106.09685. [18] A. Vaswani et al., "Attention Is All You Need," in Proc. NeurIPS, vol. 30, Long Beach, CA, 2017, pp. 5998–6008. [19] J. Kim, J. Kong, and J. Son, "Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech (VITS)," in Proc. ICML, Virtual, 2021, pp. 5530–5540. [20] Google Cloud, "Contact Center AI: Architecture and Deployment Patterns," Google LLC, Mountain View, CA, White Paper, 2023. [Online]. Available: https://cloud.google.com/solutions/contact-center |
