Efficient Haar wavelet transform for detecting saccades and blinks in real-time EOG signal

KK Gundugonti, B Narayanam - SN Computer Science, 2021 - Springer
In this study, we present an efficient Haar discrete wavelet transform architecture using
Radix-2^ r 2 r multiplier and 4: 2 compressor. The functionality of this architecture is verified …

A classification-based non-local means adaptive filtering for speech enhancement and its FPGA prototype

N Srinivas, G Pradhan, PK Kumar - Circuits, Systems, and Signal …, 2020 - Springer
Non-local mean (NLM) adaptive filtering is a well-explored technique for the denoising of
images and electrocardiogram signals. In NLM filtering, the signal value at a particular …

An approach for reducing pitch induced mismatches to detect keywords in children's speech

S Garnaik, G Pradhan, K Sethi - Multimedia Tools and Applications, 2022 - Springer
Keyword spotting (KWS) is the task of detecting some specific words of interest in a text or
speech signal. The intention or context of a conversation posted on different social platforms …

A simplified realization of zero frequency filter for hardware implementation

N Srinivas, G Pradhan, D Govind - Circuits, Systems, and Signal …, 2020 - Springer
Zero frequency filtering (ZFF) is a well-explored technique for detecting glottal closure
instants (GCIs) from the speech signal. The features extracted from the ZFF of the speech …

Detection of vowels in continuous speech using variation of short-term magnitude spectra

S Garnaik, N Srinivas, G Pradhan… - TENCON 2019-2019 …, 2019 - ieeexplore.ieee.org
The prominent formants are observed in the short-term magnitude spectra (ST-MS) of
vowels. Consequently, the variance of the ST-MS is relatively more for the vowels than other …