Related papers: LISTEN: Lightweight Industrial Sound-representable…
Training deep neural networks with noise and data heterogeneity is a major challenge. We introduce Lightweight Learnable Adaptive Weighting (LiLAW), a method that dynamically adjusts the loss weight of each training sample based on its…
Exploiting big data knowledge on small devices will pave the way for building truly cognitive Internet of Things (IoT) systems. Although machine learning has led to great advancements for IoT-based data analytics, there remains a huge…
Monitoring of bird populations has played a vital role in conservation efforts and in understanding biodiversity loss. The automation of this process has been facilitated by both sensing technologies, such as passive acoustic monitoring,…
Large Audio Language Models (LALMs) have been widely applied in real-time scenarios, such as in-car assistants and online meeting comprehension. In practice, audio inputs are often corrupted by device and environmental noise, leading to…
Existing methods to recover model accuracy on analog-digital hardware in the presence of quantization and analog noise include noise-injection training. However, it can be slow in practice, incurring high computational costs, even when…
Multilingual spoken dialogue systems have gained prominence in the recent past necessitating the requirement for a front-end Language Identification (LID) system. Most of the existing LID systems rely on modeling the language discriminative…
Far-field speech recognition in noisy and reverberant conditions remains a challenging problem despite recent deep learning breakthroughs. This problem is commonly addressed by acquiring a speech signal from multiple microphones and…
Deep learning techniques for separating audio into different sound sources face several challenges. Standard architectures require training separate models for different types of audio sources. Although some universal separators employ a…
Large audio language models (LALMs) are a class of foundation models for audio understanding. Existing LALMs tend to degrade significantly in real-world noisy acoustic conditions where speech and non-speech sounds interfere. While…
This paper proposes a novel framework for audio deepfake detection with two main objectives: i) attaining the highest possible accuracy on available fake data, and ii) effectively performing continuous learning on new fake data in a…
Non-intrusive load monitoring (NILM) or energy disaggregation aims to extract the load profiles of individual consumer electronic appliances, given an aggregate load profile of the mains of a smart home. This work proposes a novel…
Instruction tuning is essential for aligning large language models (LLMs) to downstream tasks and commonly relies on large, diverse corpora. However, small, high-quality subsets, known as coresets, can deliver comparable or superior…
The deployment of AI models on low-power, real-time edge devices requires accelerators for which energy, latency, and area are all first-order concerns. There are many approaches to enabling deep neural networks (DNNs) in this domain,…
The rise of Internet of Things (IoT) devices in the physical world necessitates voice-based interfaces capable of handling complex user experiences. While modern Large Language Models (LLMs) already demonstrate strong tool-usage…
Curating foundation speech models for edge and IoT settings, where computational resources vary over time, requires dynamic architectures featuring adaptable reduction strategies. One emerging approach is layer dropping ($\mathcal{LD}$)…
Wearable audio devices with active noise control (ANC) enhance listening comfort but often at the expense of situational awareness. However, this auditory isolation may mask crucial environmental cues, posing significant safety risks. To…
This paper elucidates a model for acoustic single and multi-tone classification in resource constrained edge devices. The proposed model is of State-of-the-art Fast Accurate Stable Tiny Gated Recurrent Neural Network. This model has…
Edge computing is a distributed computing paradigm that collects and processes data at or near the source of data generation. The on-device learning at edge relies on device-to-device wireless communication to facilitate real-time data…
Voice controlled devices and services have become very popular in the consumer IoT. Cloud-based speech analysis services extract information from voice inputs using speech recognition techniques. Services providers can thus build very…
Generating accurate sounds for complex audio-visual scenes is challenging, especially in the presence of multiple objects and sound sources. In this paper, we propose an {\em interactive object-aware audio generation} model that grounds…