4 citations · 4 across the 8 of their papers we have counts for
11 papers
DriftTTS: Few-Step Text-to-Speech Without Distillation via Distribution-Matching Drift
Mohammad Nur Hossain Khan, Subrata Biswas, Bashima Islam
Few-step neural text-to-speech models often rely on short- ened diffusion or flow-matching schedules, or on distillation from pretrained multi-step teachers. To avoid these depen-…
ProcAgent: An Agentic Framework for Procedural Task Guidance on Edge with Human-in-the-Loop
Azizul Zahid, Subrata Biswas, Bashima Islam +1
Procedural tasks such as furniture assembly and home repair impose substantial cognitive demands because users must interpret instructions, track task progress, reason about spatia…
OWL: Geometry-Aware Spatial Reasoning for Audio Large Language Models
Subrata Biswas, Mohammad Nur Hossain Khan, Bashima Islam
Spatial reasoning is fundamental to auditory perception, yet current audio large language models (ALLMs) largely rely on unstructured binaural cues and single step inference. This…
UnIT: Scalable Unstructured Inference-Time Pruning for MAC-efficient Neural Inference on MCUs
Ashe Neth, Sawinder kaur, Mohammad Nur Hossain Khan +3
Existing pruning methods are typically applied during training or compile time and often rely on structured sparsity. While compatible with low-power microcontrollers (MCUs), struc…
EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception
Sanjoy Chowdhury, Subrata Biswas, Sayan Nag +7
Modern perception models, particularly those designed for multisensory egocentric tasks, have achieved remarkable performance but often come with substantial computational costs. T…
QUADS: QUAntized Distillation Framework for Efficient Speech Language Understanding
Subrata Biswas, Mohammad Nur Hossain Khan, Bashima Islam
Spoken Language Understanding (SLU) systems must balance performance and efficiency, particularly in resource-constrained environments. Existing methods apply distillation and quan…
RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language
Subrata Biswas, Mohammad Nur Hossain Khan, Bashima Islam
Multimodal question answering (QA) often requires identifying which video, audio, or sensor tokens are relevant to the question. Yet modality disagreements are common: off-camera s…
Missingness-resilient Video-enhanced Multimodal Disfluency Detection
Payal Mohapatra, Shamika Likhite, Subrata Biswas +2
Most existing speech disfluency detection techniques only rely upon acoustic data. In this work, we present a practical multimodal disfluency detection approach that leverages avai…
LLaSA: A Sensor-Aware LLM for Natural Language Reasoning of Human Activity from IMU Data
Sheikh Asif Imran, Mohammad Nur Hossain Khan, Subrata Biswas +1
Wearable systems can recognize activities from IMU data but often fail to explain their underlying causes or contextual significance. To address this limitation, we introduce two l…
Memory-efficient Energy-adaptive Inference of Pre-Trained Models on Batteryless Embedded Systems
Pietro Farina, Subrata Biswas, Eren Yıldız +4
Batteryless systems frequently face power failures, requiring extra runtime buffers to maintain inference progress and leaving only a memory space for storing ultra-tiny deep neura…
LOCUS: LOcalization with Channel Uncertainty and Sporadic Energy
Subrata Biswas, Mohammad Nur Hossain Khan, Violet Colwell +2
Accurate sound source localization (SSL), such as direction-of-arrival (DoA) estimation, relies on consistent multichannel data. However, batteryless systems often suffer from miss…