Related papers: Linear Semantic Segmentation for Low-Resource Spok…

Identifying multiple speakers without knowing where a speaker's voice is in a recording is a challenging task. In this paper, a hierarchical attention network is proposed to solve a weakly labelled speaker identification problem. The use of…

The task of topical segmentation is well studied, but previous work has mostly addressed it in the context of structured, well-defined segments, such as segmentation into paragraphs, chapters, or segmenting text that originated from…

Speaker diarization, the process of segmenting an audio stream or transcribed speech content into homogenous partitions based on speaker identity, plays a crucial role in the interpretation and analysis of human speech. Most existing…

Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing. Different from the mainstream…

The importance of building sentiment analysis tools for Arabic social media has been recognized during the past couple of years, especially with the rapid increase in the number of Arabic social media users. One of the main difficulties in…

The focus of language model evaluation has transitioned towards reasoning and knowledge-intensive tasks, driven by advancements in pretraining large models. While state-of-the-art models are partially trained on large Arabic texts,…

Unlike major Western languages, most African languages are very low-resourced. Furthermore, the resources that do exist are often scattered and difficult to obtain and discover. As a result, the data and code for existing research has…

Denoising diffusion probabilistic models have recently received much research attention since they outperform alternative approaches, such as GANs, and currently provide state-of-the-art generative performance. The superior performance of…

Large language models (LLMs) for Arabic are still dominated by Modern Standard Arabic (MSA), with limited support for Saudi dialects such as Najdi and Hijazi. This underrepresentation hinders their ability to capture authentic dialectal…

Semantic segmentation is one of the most fundamental tasks in image understanding with a long history of research, and subsequently a myriad of different approaches. Traditional methods strive to train models up from scratch, requiring vast…

Dialectal Arabic (DA) poses a persistent challenge for natural language processing (NLP), as most everyday communication in the Arab world occurs in dialects that diverge significantly from Modern Standard Arabic (MSA). This linguistic…

We present Ara-BEST-RQ, a family of self-supervised learning (SSL) models specifically designed for multi-dialectal Arabic speech processing. Leveraging 5,640 hours of crawled Creative Commons speech and combining it with publicly available…

Segmenting speech transcripts into thematic sections benefits both downstream processing and users who depend on written text for accessibility. We introduce a novel approach to hierarchical topic segmentation in transcripts, generating…

The use of multilingual language models for tasks in low and high-resource languages has been a success story in deep learning. In recent times, Arabic has been receiving widespread attention on account of its dialectal variance. While…

Scaling up the vocabulary of semantic segmentation models is extremely challenging because annotating large-scale mask labels is labour-intensive and time-consuming. Recently, language-guided segmentation models have been proposed to…

One of the major challenges for developing automatic speech recognition (ASR) for low-resource languages is the limited access to labeled data with domain-specific variations. In this study, we propose a pseudo-labeling approach to develop…

Text segmentation is a fundamental task in natural language processing, where documents are split into contiguous sections. However, prior research in this area has been constrained by limited datasets, which are either small in scale,…

Dialogue Topic Segmentation (DTS) plays an essential role in a variety of dialogue modeling tasks. Previous DTS methods either focus on semantic similarity or dialogue coherence to assess topic similarity for unsupervised dialogue…

Discrete audio tokens have recently gained considerable attention for their potential to bridge audio and language processing, enabling multimodal language models that can both generate and understand audio. However, preserving key…

We present Voxlect, a novel benchmark for modeling dialects and regional languages worldwide using speech foundation models. Specifically, we report comprehensive benchmark evaluations on dialects and regional language varieties in English,…