Scholarlink

Gender recognition by voice is a critical task with applications ranging from speech-based interfaces to forensic analysis. In this research, we proposed optimization strategies for enhancing the performance of speech recognition technology through targeted feature recognition, iterative simulation training, and integration of acoustic and contextual features. We explored the effectiveness of machine learning techniques in accurately classifying gender based on voice characteristics using CART, Random Forest, KNN, SVM, MLP, Ensemble vote models. Experiment is performed on Kaggle dataset and SVM model gives the best accuracy of 98.6%.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Decoding Gender by Voice: Exploring Machine Learning Models for Voice-Based Gender Identification

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Payanshi Jain,
  • Nonita Sharma,
  • Ritu Rani,
  • Nikita Yadav,
  • Samiksha Aggarwal

摘要

Gender recognition by voice is a critical task with applications ranging from speech-based interfaces to forensic analysis. In this research, we proposed optimization strategies for enhancing the performance of speech recognition technology through targeted feature recognition, iterative simulation training, and integration of acoustic and contextual features. We explored the effectiveness of machine learning techniques in accurately classifying gender based on voice characteristics using CART, Random Forest, KNN, SVM, MLP, Ensemble vote models. Experiment is performed on Kaggle dataset and SVM model gives the best accuracy of 98.6%.