Related papers: WolBanking77: Wolof Banking Speech Intent Classifi…
Conversational systems are of primary interest in the AI community. Chatbots are increasingly being deployed to provide round-the-clock support and to increase customer engagement. Many of the commercial bot building frameworks follow a…
We present our first efforts in building an automatic speech recognition system for Somali, an under-resourced language, using 1.57 hrs of annotated speech for acoustic model training. The system is part of an ongoing effort by the United…
The dominant way of judging Large Language Models (LLMs) has been to ask how well they can recall explicit facts from very long inputs. While today's best models achieve near perfect recall, this masks a harder skill: performing multi-step…
We developed dysarthric speech intelligibility classifiers on 551,176 disordered speech samples contributed by a diverse set of 468 speakers, with a range of self-reported speaking disorders and rated for their overall intelligibility on a…
Speech Large Language Models (SLLMs) have rapidly expanded, supporting a wide range of tasks. These models are typically evaluated using text prompts, which may not reflect real-world scenarios where users interact with speech. To address…
With the increasing popularity of daily information sharing and acquisition on the Internet, this paper introduces an innovative approach for intent classification in Bangla language, focusing on social media posts where individuals share…
As speech generation technology advances, the risk of misuse through deepfake audio has become a pressing concern, which underscores the critical need for robust detection systems. However, many existing speech deepfake datasets are limited…
Deception is a fundamental challenge for multi-agent reasoning: effective systems must strategically conceal information while detecting misleading behavior in others. Yet most evaluations reduce deception to static classification, ignoring…
In this work, we present AfriHuBERT, an extension of mHuBERT-147, a compact self-supervised learning (SSL) model pretrained on 147 languages. While mHuBERT-147 covered 16 African languages, we expand this to 1,226 through continued…
Language models exhibit systematic performance gaps when processing text in non-standard language varieties, yet their ability to comprehend variety-specific slang remains underexplored for several languages. We present a comprehensive…
The performance of Artificial Intelligence (AI) systems fundamentally depends on high-quality training data. However, low-resource languages like Arabic suffer from severe data scarcity. Moreover, the absence of child-specific speech…
Intent classification is crucial for conversational agents (chatbots), and deep learning models perform well in this area. However, little research has been done on the explainability of intent classification due to the absence of suitable…
Bengali is spoken by over 230 million people yet remains severely under-served in automatic speech recognition (ASR) and speaker diarization research. In this paper, we present our system for the DL Sprint 4.0 Bengali Long-Form Speech…
Research into the area of multiparty dialog has grown considerably over recent years. We present the Molweni dataset, a machine reading comprehension (MRC) dataset with discourse structure built over multiparty dialog. Molweni's source…
Current speech language models generate responses directly without explicit reasoning, leading to errors that cannot be corrected once audio is produced. We introduce \textbf{``Silent Thought, Spoken Answer''} -- a paradigm where speech…
This work presents a scalable solution to open-vocabulary visual speech recognition. To achieve this, we constructed the largest existing visual speech recognition dataset, consisting of pairs of text and video clips of faces speaking…
This paper focuses on wake on intent (WOI) techniques for platforms with limited compute and memory. Our approach of utterance-level intent classification is based on a sequence of keywords in the utterance instead of a single fixed key…
We present the Thiomi Dataset, a large-scale multimodal corpus spanning ten African languages across four language families: Swahili, Kikuyu, Kamba, Kimeru, Luo, Maasai, Kipsigis, Somali (East Africa); Wolof (West Africa); and Fulani…
We explore the benefits that multitask learning offer to speech processing as we train models on dual objectives with automatic speech recognition and intent classification or sentiment classification. Our models, although being of modest…
Pretrained language models (PLMs) for African languages are continually improving, but the reasons behind these advances remain unclear. This paper presents the first systematic investigation into probing PLMs for linguistic knowledge about…