4 March 2014 in IETE Technical Review
The overall success of automatic speech recognition (ASR) depends on efficient phoneme recognition performance and quality of speech signal received in ASR. However, dissimilar inputs of speakers affect the overall recognition performance. One of the main problems that affect recognition performance is inter-speaker variability. Vocal tract length normalization (VTLN) is introduced to compensate inter-speaker variation on the speaker signal by applying speaker-specific warping of the frequency scale of a filter bank. Instead of measuring the performance on word level with speaker-specific warping, this research focuses on direct tackling at the phoneme level and applying VTLN on all speakers’ speech signals to analyse the best setting for the highest recognition performance. This research seeks to compare each phoneme recognition results from warping factor between 0.74 and 1.54 with 0.02 increments on nine different ranges of frequency warping boundary. The warp factor and frequency warping range that provides the highest phoneme recognition performance is applied on word recognition. The results show an improved performance in phoneme recognition by 0.7% and spoken word recognition by 0.5% using warp factor of 1.40 on frequency range of 300–5000 Hz in comparison to baseline results.
17 February 2024 in Journal of Advanced Research in Computing and Applications
Natural user interface (NUI) is an interface that enables users to interact with the digital world in the same way they interact with the physical world through sensory input such as touch, speech, and gesture. The combination of multiple modalities for NUI has become the trend in user interface recently. There is significant progress in advancing speech and hand recognition technology, which makes both become effective input modalities in HCI. However, there are limitations exist that degrade the performance which includes the complexity of vocabulary and unnatural hand gestures to instruct the machine. Therefore, this project aims to develop an application with natural gesture and speech input for 3D object manipulation. Three phases have been carried out, first is data collection and analysis, second is application structure design, and the third is the implementation of speech and gesture in 3D object manipulation. This application is developed by using Leap Motion Controller for hand gesture tracking, and Microsoft Azure Speech Cognitive Service and Microsoft Azure Language Understanding Intelligence Service for natural language speech recognition. The evaluation has been performed based on the accuracy of the command recognition and usability and user acceptance. The results show that the approaches developed in this project able to make good recognition of the speech command and gesture interaction while user experience testing shows high level of satisfaction in the application.
25 November 2024 in International Journal of Innovative Computing
Active learning can help reduce the labeling burden in training deep object detection models by strategically selecting the most informative data points for labeling from unlabeled data. Different approaches to this task have been proposed in recent years, with differences often found in their approaches to the specific components. Consequently, this study breaks down active learning methods into their individual components and examines the diverse strategies associated with each intending to shed light on areas that have not yet been explored in depth. Doing so, the study offers valuable insights into potential research directions in this area.