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

An In-Depth Investigation into Automatic Dubbing Leveraging ASR, Machine Translation and Deep Voice 3

  • K. Hema Priya,
  • N. Akhilan,
  • R. Aravindh,
  • K. Janardhana

摘要

In the context of India's rich linguistic diversity, where hundreds of regional languages are spoken, ensuring accessibility and inclusivity in audio-visual content is paramount. To tackle this challenge, the work is aimed at developing an innovative solution for translating English-language video content into Indian regional language. Leveraging state-of-the-art technologies in speech recognition and text-to-speech synthesis, our methodology focuses on transcribing English audio dialogues and producing an audio track in target regional languages. The work aims to address this challenge by developing an innovative solution that automates the process of translating English-language video content into multiple Indian regional languages. We do this with advanced video processing techniques to match the dubbed audio with the original video while maintaining video quality. This solution not only enhances inclusivity but also facilitates cultural exchange and the dissemination of knowledge and entertainment across India's linguistic landscape.