arXiv subjects

Sahil Gangurde

Publications and source records attributed to Sahil Gangurde.

3 recordsLinked to original sources

arXiv2026

AudioTQ: A Data-Oblivious 6-Bit CPU Audio Codec via Randomized Hadamard Rotation and Lloyd-Max Quantization

Lossy audio compression algorithms traditionally rely on psychoacoustic modeling and frequency-domain representations (e.g., MP3, AAC, and Opus) to discard information that is imperceptible to the human auditory system. While highly effective, these approaches are computationally complex and domain-specific. In this paper, we present the design and mathematical formulation of AudioTQ, a data-oblivious lossy audio codec that operates directly in the time domain. Inspired by Large Language Model (LLM) weight quantization techniques (specifically the TurboQuant framework), AudioTQ uniformizes volatile time-domain amplitudes into a predictable standard normal distribution using an orthonormal, randomized Fast Walsh-Hadamard Transform (FWHT) rotation. This enables coordinate-wise scalar quantization using an offline-trained, MSE-optimal 6-bit Lloyd-Max quantizer, augmented by a 1-bit Quantized Joint Least-Squares (QJL) residual correction layer. The resulting 7-bit virtual indices are packed into native 8-bit containers, aligning with standard CPU register boundaries to ensure real-time single-threaded execution without hardware parallel accelerators. We detail the bitwise reconstruction of 24-bit studio stems, analyze the butterfly network of the FWHT, derive the mathematical failure modes under sparse inputs, and present benchmarks showing up to 74.4% physical size reduction alongside a Signal-to-Quantization-Noise Ratio (SQNR) of ~30 dB.

cs.SD↗

arXiv2023

Building and Road Segmentation Using EffUNet and Transfer Learning Approach

In city, information about urban objects such as water supply, railway lines, power lines, buildings, roads, etc., is necessary for city planning. In particular, information about the spread of these objects, locations and capacity is needed for the policymakers to make impactful decisions. This thesis aims to segment the building and roads from the aerial image captured by the satellites and UAVs. Many different architectures have been proposed for the semantic segmentation task and UNet being one of them. In this thesis, we propose a novel architecture based on Google's newly proposed EfficientNetV2 as an encoder for feature extraction with UNet decoder for constructing the segmentation map. Using this approach we achieved a benchmark score for the Massachusetts Building and Road dataset with an mIOU of 0.8365 and 0.9153 respectively.

cs.CV↗

arXiv2020

LSB Steganography Using Pixel Locator Sequence with AES

Image steganography is the art of hiding data into images. Secret data such as messages, audio, images can be hidden inside the cover image. This is mainly achieved by hiding the data into the LSB(Least Significant Bit) of the image pixels. To improve the security of steganography, this paper studied data encryption with AES(Advanced Encryption Standard) and LSB based data hiding technique with advanced user-defined encrypted data distribution in pixels other than the common linear computational method of storing data in a linear form. This data distribution file will contain the location of the data(in form of pixel numbers) to be encrypted/decrypted which is further encrypted with AES thus providing double encryption for data and its location stored over pixels. Steganography has many applications such as medical, military, copyright information, etc.

cs.CR↗