相关论文: NoLoR: An ASR-Based Framework for Expedited Endang…

End-to-end transformer-based models epitomize the cutting-edge in Automatic Speech Recognition (ASR) systems. Despite their substantial benefits, these models demand extensive training data to perform optimally, presenting a significant…

Automatic Speech Recognition (ASR) has increasing utility in the modern world. There are a many ASR models available for languages with large amounts of training data like English. However, low-resource languages are poorly represented. In…

We present a novel Speech Augmented Language Model (SALM) with {\em multitask} and {\em in-context} learning capabilities. SALM comprises a frozen text LLM, a audio encoder, a modality adapter module, and LoRA layers to accommodate speech…

Aligning with ACL 2022 special Theme on "Language Diversity: from Low Resource to Endangered Languages", we discuss the major linguistic and sociopolitical challenges facing development of NLP technologies for African languages. Situating…

Despite comprising one-third of global languages, African languages are critically underrepresented in Artificial Intelligence (AI), threatening linguistic diversity and cultural heritage. Ghanaian languages, in particular, face an alarming…

We present advances in the development of a FST-based morphological analyzer and generator for Skolt Sami. Like other minority Uralic languages, Skolt Sami exhibits a rich morphology, on the one hand, and there is little golden standard…

Denoising language models (DLMs) have been proposed as a powerful alternative to traditional language models (LMs) for automatic speech recognition (ASR), motivated by their ability to use bidirectional context and adapt to a specific ASR…

Automatic Speech Recognition (ASR) technologies have transformed human-computer interaction; however, low-resource languages in Africa remain significantly underrepresented in both research and practical applications. This study…

This study investigates the efficacy of data augmentation techniques for low-resource automatic speech recognition (ASR), focusing on two endangered Austronesian languages, Amis and Seediq. Recognizing the potential of self-supervised…

Despite representing nearly one-third of the world's languages, African languages remain critically underserved by modern NLP technologies, with 88\% classified as severely underrepresented or completely ignored in computational…

Recent breakthroughs in NLP largely increased the presence of ASR systems in our daily lives. However, for many low-resource languages, ASR models still need to be improved due in part to the difficulty of acquiring pertinent data. This…

Automatic speech recognition (ASR) systems often need to be developed for extremely low-resource languages to serve end-uses such as audio content categorization and search. While universal phone recognition is natural to consider when no…

We present an open-source online dictionary editing system, Ve'rdd, that offers a chance to re-evaluate and edit grassroots dictionaries that have been exposed to multiple amateur editors. The idea is to incorporate community activities…

Coreference Resolution (CR) is a fundamental NLP task critical for long-form tasks as information extraction, summarization, and many business applications. However, CR methods originally designed for English struggle with Morphologically…

Multilingual retrieval increasingly underpins cross-lingual question answering and retrieval-augmented generation. Strong zero-shot scores on multilingual benchmarks are often taken as evidence that current encoders transfer reliably across…

The digital exclusion of endangered languages remains a critical challenge in NLP, limiting both linguistic research and revitalization efforts. This study introduces the first computational investigation of Comanche, an Uto-Aztecan…

Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios.…

Automatic speech recognition for low-resource languages remains fundamentally constrained by the scarcity of labeled data and computational resources required by state-of-the-art models. We present a systematic investigation into…

In recent years, the enhanced capabilities of ASR models and the emergence of multi-dialect datasets have increasingly pushed Arabic ASR model development toward an all-dialect-in-one direction. This trend highlights the need for…

Named Entity Recognition (NER) is a fundamental NLP task, commonly formulated as classification over a sequence of tokens. Morphologically-Rich Languages (MRLs) pose a challenge to this basic formulation, as the boundaries of Named Entities…