Related papers: The Esethu Framework: Reimagining Sustainable Data…
The scarcity of large-scale, open-source data for dialects severely hinders progress in speech technology, a challenge particularly acute for the widely spoken Sichuanese dialects of Chinese. To address this critical gap, we introduce…
South Africa's escalating mental health crisis, compounded by limited access to culturally responsive care, calls for innovative and contextually grounded interventions. While large language models show considerable promise for mental…
Sustainable Development Goals (SDGs) bring together the diverse development community and provide a clear set of development targets for 2030. Given a large number of actors and initiatives related to these goals, there is a need to have a…
The BabyLM challenge called on participants to develop sample-efficient language models. Submissions were pretrained on a fixed English corpus, limited to the amount of words children are exposed to in development (<100m). The challenge…
Recent advancements in Speech Large Language Models have significantly enhanced multi-dimensional speech understanding. However, the majority of high-performance frameworks are predominantly optimized for GPU centric ecosystems and…
Toxic language is one of the major barrier to safe online participation, yet robust mitigation tools are scarce for African languages. This study addresses this critical gap by investigating automatic text detoxification (toxic to neutral…
Most speech and language technologies are trained with massive amounts of speech and text information. However, most of the world languages do not have such resources or stable orthography. Systems constructed under these almost zero…
Spoken dialog systems are slowly becoming and integral part of the human experience due to their various advantages over textual interfaces. Spoken language understanding (SLU) systems are fundamental building blocks of spoken dialog…
Natural Language Processing is a crucial frontier in artificial intelligence, with broad applications in many areas, including public health, agriculture, education, and commerce. However, due to the lack of substantial linguistic…
Despite the significant progress in end-to-end (E2E) automatic speech recognition (ASR), E2E ASR for low resourced code-switching (CS) speech has not been well studied. In this work, we describe an E2E ASR pipeline for the recognition of CS…
Zero-resource speech technology is a growing research area that aims to develop methods for speech processing in the absence of transcriptions, lexicons, or language modelling text. Early term discovery systems focused on identifying…
Recent advances in speech-enabled language models have shown promising results in building intelligent voice assistants. However, most existing approaches rely on large-scale paired speech-text data and extensive computational resources,…
A major focus of recent research in spoken language understanding (SLU) has been on the end-to-end approach where a single model can predict intents directly from speech inputs without intermediate transcripts. However, this approach…
Speech processing for low-resource dialects remains a fundamental challenge in developing inclusive and robust speech technologies. Despite its linguistic significance and large speaker population, the Wu dialect of Chinese has long been…
Despite remarkable advances in natural language processing, developing effective systems for low-resource languages remains a formidable challenge, with performances typically lagging far behind high-resource counterparts due to data…
Bootstrapping speech recognition on limited data resources has been an area of active research for long. The recent transition to all-neural models and end-to-end (E2E) training brought along particular challenges as these models are known…
ASR has achieved remarkable global progress, yet African low-resource languages remain rigorously underrepresented, producing barriers to digital inclusion across the continent with more than +2000 languages. This systematic literature…
Spoken Language Understanding (SLU) plays a crucial role in speech-centric multimedia applications, enabling machines to comprehend spoken language in scenarios such as meetings, interviews, and customer service interactions. SLU…
This paper presents KIT's submissions to the IWSLT 2025 low-resource track. We develop both cascaded systems, consisting of Automatic Speech Recognition (ASR) and Machine Translation (MT) models, and end-to-end (E2E) Speech Translation (ST)…
Climate change has intensified the need for transparency and accountability in organizational practices, making Environmental, Social, and Governance (ESG) reporting increasingly crucial. Frameworks like the Global Reporting Initiative…