A Pipeline for Speech-to-Text Summarization and Question Identification for Enhanced Chatbot Interactions
- Title
- A Pipeline for Speech-to-Text Summarization and Question Identification for Enhanced Chatbot Interactions
- Creator
- Jerusha, B.; Sunil, Aleena Rose K; Yogish, Deepa
- Description
- The rapid advancements in natural language processing provide strong support for the new potential application of integrating Google Speech Recognition API, BART, and BERT to create a full pipeline for speech recognition, text summarization and question answering without breaking human interaction. The research aims to develop such a holistic pipeline involves integrating the Google Speech Recognition API to perform speech-to-text, BART for text summarization, and finally BERT for question answering based on both the summary and original transcript. The system was tested under various criteria such as testing accuracy, real-time processing performance, and stress tests for scalability where the findings include an average of 60% text compression with BART, an 88% accuracy in BERT-based question answering, and scores indicating high user satisfaction (4.3/5). Real-time processing latency can be able to cater to interaction within 2-3 seconds and the capacity of the system has proven without performance loss during simultaneous users. The research done can practically find applications in areas like intelligent virtual assistants, customer service automation and e-learning applications that improve accessibility and user experience. 2025 IEEE.
- Source
- Proceedings of 3rd IEEE International Conference on Knowledge Engineering and Communication Systems, ICKECS 2025;
- Date
- 01-01-2025
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Subject
- BART; BERT; Google Speech Recognition; Multi-modal NLP; Natural Language Processing; Question Answering; Speech-to-Text; Text Summarization
- Coverage
- Jerusha B., Christ University, School of Engineering and Technology, Department of Cse, Bengaluru, India; Sunil A.R.K., Christ University, School of Engineering and Technology, Department of Cse, Bengaluru, India; Yogish D., Christ University, School of Engineering and Technology, Department of Cse, Bengaluru, India
- Rights
- Restricted Access; Hardcopy may be available in the library
- Relation
- ISBN: 979-833153701-2;
- Format
- online
- Language
- English
- Type
- Conference paper
Collection
Citation
Jerusha, B.; Sunil, Aleena Rose K; Yogish, Deepa, “A Pipeline for Speech-to-Text Summarization and Question Identification for Enhanced Chatbot Interactions,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 18, 2026, https://archives.christuniversity.in/items/show/26053.