Current Trends in Signal Processing
Volume 1, Issue 1-3 (2025)
Published
Table of contents
-
Localization Based Beamforming Approach to Audio Source Separation from Binaural Mixtures
Abstract: This paper presents an approach of localization on the basis of audio source separation from binaural mixtures with adaptive beamforming. A new source localization technique is proposed to spatially localize the sources with two degrees of freedom (azimuth and elevation). We used a head related transfer function to synthesize the binaural mixture that introduces the interaural differences to the source signals. The interaural cues are technically employed to estimate the …
Published in Current Trends in Signal Processing · Vol. 1, Issue 1-3, 2025 · pp. 1–10 Read article
-
Numerals Recognition for Urdu Script
Abstract: Optical Character Recognition is a difficult task due to the complexities of the script and varying location of the character in the image. Characters of Urdu script-based languages are even more difficult to recognize but they have not received much attention in spite of the fact that Urdu ranks sixth in the top 10 most-spoken primary languages (181 million people). The problem of numeral recognition in Urdu is due to …
Published in Current Trends in Signal Processing · Vol. 1, Issue 1-3, 2025 · pp. 11–16 Read article
-
Online Change Detection Algorithm Based on the Continuous Wavelet Transform, the CUSUM Algorithm and an Autoregressive Model
Abstract: In this article, we present a change point detection algorithm based on the continuous wavelet transform, the CUSUM algorithm and an autoregressive model. At the beginning of the article, we describe a necessary transformation of a signal which has to be made for the purpose of change detection. Then case study related to iron ore sinter production which can be solved using our proposed technique is discussed. After that, we …
Published in Current Trends in Signal Processing · Vol. 1, Issue 1-3, 2025 · pp. 17–29 Read article
-
Optical Character Recognition of 10 × 10 Size Binary Images
Abstract: Ten binary images of size 10 × 10 for each of the decimal numbers from 0 to 9 are considered for the simulation setup. Applying different processing techniques on these images, information contents were extracted. Initially, no noise was added in these images and character recognition of 100% was obtained. After that, noise is added in these images (i.e., images were distorted) but even then 9 out of 10 images …
Published in Current Trends in Signal Processing · Vol. 1, Issue 1-3, 2025 · pp. 30–32 Read article
-
Principal Component Analysis Based Dominant Features Selection Method for Speaker Identification
Abstract: Cepstrum based features are mostly used in speaker identification. Mel-frequency cepstrum coefficients (MFCCs) and their statistical properties (skewness, kurtosis and standard deviation) are used in this paper for text-dependent speaker identification. Principal component analysis (PCA) is employed to select the dominant feature vector representing the speaker characteristics. Multi-layer neural network is used as the classification engine. There occurs the inter-speaker variation of speech length uttering the same word. The feature …
Published in Current Trends in Signal Processing · Vol. 1, Issue 1-3, 2025 · pp. 33–45 Read article