Generating Meeting Transcription Using Natural Language Processing

Natural Language Processing plays a pivotal role in automating the transcription of meetings. It enables machines to understand, interpret, and generate human language. In meeting transcription, NLP components such as Automatic Speech Recognition (ASR), speaker diarization, entity recognition, summarization, and sentiment analysis work together to produce accurate and readable transcripts. ASR converts spoken words into text, while NLP refines the raw output by correcting grammatical errors, identifying speakers, and structuring dialogue for readability and comprehension. Ethical considerations, including data privacy and bias in multilingual environments, are also examined. The findings suggest that NLP-driven transcription tools not only simplify record-keeping but also offer valuable insights for decision-making and knowledge management. As technology advances, such tools are poised to become essential in professional settings, providing reliable, scalable solutions with minimal human intervention. This research focusses on leveraging NLP models for generating machine transcripts. The word error rate (WER) and character error rate (CER) have been chosen as the performance metrics. Keywords: Natural Language Processing (NLP), Meeting Transcriptions, wav2vec, Whisper, Word Error Rate (WER), Character Error Rate (CER).