相关论文: Learnings from Technological Interventions in a Lo…

The performance of multilingual pretrained models is highly dependent on the availability of monolingual or parallel text present in a target language. Thus, the majority of the world's languages cannot benefit from recent progress in NLP…

The recent advances in Natural Language Processing have been a boon for well-represented languages in terms of available curated data and research resources. One of the challenges for low-resourced languages is clear guidelines on the…

Publicly available TTS datasets for low-resource languages like Hindi and Tamil typically contain 10-20 hours of data, leading to poor vocabulary coverage. This limitation becomes evident in downstream applications where domain-specific…

Low-resource language varieties used by specific groups remain neglected in the development of Multilingual Language Models. A great deal of cross-lingual research focuses on inter-lingual language transfer which strives to align allied…

Hate speech is a global phenomenon, but most hate speech datasets so far focus on English-language content. This hinders the development of more effective hate speech detection models in hundreds of languages spoken by billions across the…

Spoken Term Detection (STD) is the task of searching for words or phrases within audio, given either text or spoken input as a query. In this work, we use state-of-the-art Hindi, Tamil and Telugu ASR systems cross-lingually for lexical…

Neural machine translation has become the state-of-the-art for language pairs with large parallel corpora. However, the quality of machine translation for low-resource languages leaves much to be desired. There are several approaches to…

Rapid developments of large language models have revolutionized many NLP tasks for English data. Unfortunately, the models and their evaluations for low-resource languages are being overlooked, especially for languages in South Asia.…

Although researchers and practitioners are pushing the boundaries and enhancing the capacities of NLP tools and methods, works on African languages are lagging. A lot of focus on well resourced languages such as English, Japanese, German,…

Training multilingual automatic speech recognition (ASR) systems is challenging because acoustic and lexical information is typically language specific. Training multilingual system for Indic languages is even more tougher due to lack of…

Developing Automatic Speech Recognition (ASR) for low-resource languages is a challenge due to the small amount of transcribed audio data. For many such languages, audio and text are available separately, but not audio with transcriptions.…

This report evaluates the performance of text-in text-out Large Language Models (LLMs) to understand and generate Indic languages. This evaluation is used to identify and prioritize Indic languages suited for inclusion in safety benchmarks.…

This study examines the digital representation of African languages and the challenges this presents for current language detection tools. We evaluate their performance on Yoruba, Kinyarwanda, and Amharic. While these languages are spoken…

Recent speech technologies have led to produce high quality synthesised speech due to recent advances in neural Text to Speech (TTS). However, such TTS models depend on extensive amounts of data that can be costly to produce and is hardly…

End-to-end text-to-speech (TTS) has shown great success on large quantities of paired text plus speech data. However, laborious data collection remains difficult for at least 95% of the languages over the world, which hinders the…

India is home to a multitude of languages of which 22 languages are recognised by the Indian Constitution as official. Building speech based applications for the Indian population is a difficult problem owing to limited data and the number…

This paper introduces Chain of Translation Prompting (CoTR), a novel strategy designed to enhance the performance of language models in low-resource languages. CoTR restructures prompts to first translate the input context from a…

Millions of people in African countries face barriers to accessing healthcare due to language and literacy gaps. This research tackles this challenge by transforming complex medical documents -- in this case, prosthetic device user manuals…

Multilingual large language models (LLMs) are expensive to pretrain and often suffer from imbalances across languages and datasets, English-centric bias, tokenizer oversegmentation for morphologically rich low-resource languages, and the…

Recent advancements in text-to-speech (TTS) synthesis show that large-scale models trained with extensive web data produce highly natural-sounding output. However, such data is scarce for Indian languages due to the lack of high-quality,…