Development and analysis of Punjabi ASR system for mobile phones under different acoustic models

摘要

Speech technology is widely gaining importance in our daily life. Speech based mobile phone applications are becoming popular in masses due to their usability and ease of access. Speech technology is helping people, with disabilities like blindness and physical abnormalities, to access and control mobile phone applications through voice, without using keypad or touchpad. Punjabi is one of the widely spoken language in various parts of the world. In this paper, an automatic speech recognition (ASR) system for mobile phone applications in Punjabi has been proposed and implemented for four different acoustic models- context independent, context dependent untied, context dependent tied, and context dependent deleted interpolation models. The proposed ASR is evaluated at 4, 16, 32 and 64 GMMs for performance analysis in terms of parameters like accuracy, word error rate and storage space required. It is observed that context dependent untied models outperform others by having better accuracy and lower word error rate, while context independent models require less storage space than others. The choice of fruitful acoustic model depends upon the available storage space as well as desired recognition accuracy. Mobile phones having limited resources may use context independent models, while context dependent untied models can be used to develop ASR system for high end mobile phones.