Related papers: Boosting keyword spotting through on-device learna…

This paper introduces a lightweight deep learning model for real-time speech enhancement, designed to operate efficiently on resource-constrained devices. The proposed model leverages a compact architecture that facilitates rapid inference…

This study presents a proof of concept for a contactless elevator operation system aimed at minimizing human intervention while enhancing safety, intelligence, and efficiency. A microcontroller-based edge device executing tiny Machine…

End-to-end approaches have recently become popular as a means of simplifying the training and deployment of speech recognition systems. However, they often require large amounts of data to perform well on large vocabulary tasks. With the…

The use of lightweight machine learning (ML) models in internet of things (IoT) networks enables resource constrained IoT devices to perform on-device inference for several critical applications. However, the inference accuracy deteriorates…

In this paper we aim to automatically discover high quality frame-level speech features and acoustic tokens directly from unlabeled speech data. A Multi-granular Acoustic Tokenizer (MAT) was proposed for automatic discovery of multiple sets…

Human Activity Recognition (HAR) with different sensing modalities requires both strong generalization across diverse users and efficient personalization for individuals. However, conventional HAR models often fail to generalize when faced…

Task oriented language understanding in dialog systems is often modeled using intents (task of a query) and slots (parameters for that task). Intent detection and slot tagging are, in turn, modeled using sentence classification and word…

Grounding textual phrases in visual content is a meaningful yet challenging problem with various potential applications such as image-text inference or text-driven multimedia interaction. Most of the current existing methods adopt the…

Adapting a neural text-to-speech (TTS) model to a target speaker typically involves fine-tuning most if not all of the parameters of a pretrained multi-speaker backbone model. However, serving hundreds of fine-tuned neural TTS models is…

While machine learning techniques are traditionally resource intensive, we are currently witnessing an increased interest in hardware and energy efficient approaches. This need for resource-efficient machine learning is primarily driven by…

Tiny machine learning (TinyML) in IoT systems exploits MCUs as edge devices for data processing. However, traditional TinyML methods can only perform inference, limited to static environments or classes. Real case scenarios usually work in…

We consider the problem of fully unsupervised learning of grammatical (part-of-speech) categories from unlabeled text. The standard maximum-likelihood hidden Markov model for this task performs poorly, because of its weak inductive bias and…

This paper explores a simple method for improving the zero-shot learning abilities of language models. We show that instruction tuning -- finetuning language models on a collection of tasks described via instructions -- substantially…

In this article gesture recognition and speech recognition applications are implemented on embedded systems with Tiny Machine Learning (TinyML). It features 3-axis accelerometer, 3-axis gyroscope and 3-axis magnetometer. The gesture…

This paper proposes a novel MoE-based speaker adaptation framework for foundation models based dysarthric speech recognition. This approach enables zero-shot adaptation and real-time processing while incorporating domain knowledge. Speech…

Data-to-text generation systems aim to generate text descriptions based on input data (often represented in the tabular form). A typical system uses huge training samples for learning the correspondence between tables and texts. However,…

Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen classes to the unseen classes. Existing methods of obtaining class…

We introduce a new unsupervised task, spoken language modeling: the learning of linguistic representations from raw audio signals without any labels, along with the Zero Resource Speech Benchmark 2021: a suite of 4 black-box, zero-shot…

Large Language Models (LLMs) have demonstrated impressive capabilities for text rewriting. Nonetheless, the large sizes of these models make them impractical for on-device inference, which would otherwise allow for enhanced privacy and…

Advances in Tiny Machine Learning (TinyML) have bolstered the creation of smart industry solutions, including smart agriculture, healthcare and smart cities. Whilst related research contributes to enabling TinyML solutions on constrained…