Related papers: Fast, Not Fancy: Rethinking G2P with Rich Data and…

Data for human-human spoken dialogues for research and development are currently very limited in quantity, variety, and sources; such data are even scarcer in healthcare. In this work, we investigate fast prototyping of a dialogue…

Deepfakes represent a growing concern across domains such as disinformation, fraud, and non-consensual media. In particular, the rise of video conference and identity-driven attacks in high-stakes scenarios--such as impostor hiring--demands…

With the rapid advancement of generative AI, multimodal deepfakes, which manipulate both audio and visual modalities, have drawn increasing public concern. Currently, deepfake detection has emerged as a crucial strategy in countering these…

Recent studies have addressed intricate phonological phenomena in French, relying on either extensive linguistic knowledge or a significant amount of sentence-level pronunciation data. However, creating such resources is expensive and…

Graph neural networks (GNNs) have emerged as the state of the art for a variety of graph-related tasks and have been widely used in Heterogeneous Graphs (HetGs), where meta-paths help encode specific semantics between various node types.…

Synthetic datasets are widely used for training urban scene recognition models, but even highly realistic renderings show a noticeable gap to real imagery. This gap is particularly pronounced when adapting to a specific target domain, such…

In this work, we investigate the challenging problem of on-demand semantic communication over heterogeneous wireless networks. We propose a fidelity-adjustable semantic transmission framework (FAST) that empowers wireless devices to send…

Despite the recent significant advances witnessed in end-to-end (E2E) ASR system for code-switching, hunger for audio-text paired data limits the further improvement of the models' performance. In this paper, we propose a decoupled…

Spoken Grammatical Error Correction (SGEC) and Feedback (SGECF) are crucial for second language learners, teachers and test takers. Traditional SGEC systems rely on a cascaded pipeline consisting of an ASR, a module for disfluency detection…

The deployment and scaling of large language models (LLMs) have become critical as they permeate various applications, demanding high-throughput and low-latency serving systems. Existing frameworks struggle to balance these requirements,…

Long-context training of large language models (LLMs) is commonly distributed with Context Parallelism (CP) and Head Parallelism (HP), but existing training systems largely assume homogeneous GPU meshes. This paper extends CP and HP to…

Deep learning-based speech enhancement has seen huge improvements and recently also expanded to full band audio (48 kHz). However, many approaches have a rather high computational complexity and require big temporal buffers for real time…

Large language models (LLMs) excel at generating contextually relevant content. However, tailoring these outputs to individual users for effective personalization is a significant challenge. While rich user-specific information often exists…

Homophone normalization, where characters that have the same sound in a writing script are mapped to one character, is a pre-processing step applied in Amharic Natural Language Processing (NLP) literature. While this may improve performance…

Transformer-based models have made tremendous impacts in natural language generation. However the inference speed is a bottleneck due to large model size and intensive computing involved in auto-regressive decoding process. We develop…

In recent times, the emergence of Large Language Models (LLMs) has resulted in increasingly larger model size, posing challenges for inference on low-resource devices. Prior approaches have explored offloading to facilitate low-memory…

Flip through any book or listen to any song lyrics, and you will come across pronouns that, in certain cases, can hinder meaning comprehension, especially for machines. As the role of having cognitive machines becomes pervasive in our…

Large language models (LLM)-based speech synthesis has been widely adopted in zero-shot speech synthesis. However, they require a large-scale data and possess the same limitations as previous autoregressive speech models, including slow…

Recent years have witnessed significant advancements in self-supervised learning (SSL) methods for speech-processing tasks. Various speech-based SSL models have been developed and present promising performance on a range of downstream tasks…

Speech enhancement is a fundamental challenge in signal processing, particularly when robustness is required across diverse acoustic conditions and microphone setups. Deep learning methods have been successful for speech enhancement, but…