IIT Indore Develops AI Tool HGAST To Fix Gender Bias In Speech Translation From English To Hindi, Marathi And Gujarati
Indore (Madhya Pradesh): Researchers at the Indian Institute of Technology (IIT) Indore have developed a new artificial intelligence (AI)-based speech translation tool to address a common but overlooked challenge in multilingual AI systems — incorrect gender identification during translation. The newly developed tool, called HGAST (Hierarchical Gender Arbitration for Speech Translation), helps…
Indore, Madhya Pradesh: Researchers at the Indian Institute of Technology (IIT) Indore have created a new AI-powered speech translation tool, HGAST (Hierarchical Gender Arbitration for Speech Translation), to tackle a prevalent yet neglected problem in multilingual AI systems — inaccurate gender identification when translating English speech to Indian languages like Hindi, Marathi, and Gujarati.
The tool aims to minimize gender bias in artificial intelligence translation, particularly in languages where verb forms and sentence structures are influenced by the speaker's gender. Unlike English, which does not use gender-specific verb forms, Indian languages require verb changes based on the speaker's gender. For instance, in Hindi, a male speaker would say "gaya" while a female would use "gayi" to convey the same meaning.
Studies revealed that many AI translation models are trained on datasets favoring masculine language patterns, resulting in AI-generated translations with incorrect gender representations when a woman's English speech is translated into Hindi, Marathi, or Gujarati.
Written by urgent.news from Free Press Journal's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
