- Version
- Download 72
- File Size 1.07 MB
- File Count 1
- Create Date 24/06/2022
- Last Updated 25/06/2022
Speech Recognition System in Regional Language based on AI and Machine Learning
O S KOUSHIK1, T M SRINIVASA2, Dr. SUMA S3
1PG Student, MCA, DSCE, Bangalore
2Assistant. Prof., Dept. of Computer Science and Engineering NIT Calicut, Kerala
3Associate Prof., Dept. of MCA, DSCE, Bangalore
Abstract - The most emerging technologies that are being used all over the globe today for real-time applications are Machine learning and artificial intelligence. Machine learning has many potential applications, including chatbots, data processing, industrial automation, and autonomous transport vehicles, amongst many others. On the contrary, the language processing system helps in voice recognition. It makes the device more versatile and reliable in terms of the background sound, languages, and sound frequency in the area where the user is. Consequently, it recognizes and responds to the regional language. When presented with abstract data, a computer system is trained via machine learning to make accurate predictions from the given data. Using methods from Natural Language Processing and Speech Recognition, the central theme is to design an automated system capable of recognizing the voices of speakers of regional languages.
Key Words: Artificial Neural Networks, Hidden Markov models, regional language, Machine Learning, Natural language processing system