Related papers: Multilingual training set selection for ASR in und…

Recent methods in speech and language technology pretrain very LARGE models which are fine-tuned for specific tasks. However, the benefits of such LARGE models are often limited to a few resource rich languages of the world. In this work,…

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…

In this work, we explore multiple architectures and training procedures for developing a multi-speaker and multi-lingual neural TTS system with the goals of a) improving the quality when the available data in the target language is limited…

Reproducible benchmarks are crucial in driving progress of machine translation research. However, existing machine translation benchmarks have been mostly limited to high-resource or well-represented languages. Despite an increasing…

In recent years, sentiment analysis has gained significant importance in natural language processing. However, most existing models and datasets for sentiment analysis are developed for high-resource languages, such as English and Chinese,…

For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many times, degrading generalization. Two remedies exist: aggressive hyperparameter tuning such…

Models pre-trained on multiple languages have shown significant promise for improving speech recognition, particularly for low-resource languages. In this work, we focus on phoneme recognition using Allosaurus, a method for multilingual…

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing…

This paper proposes an approach to cross-language sentence selection in a low-resource setting. It uses data augmentation and negative sampling techniques on noisy parallel sentence data to directly learn a cross-lingual embedding-based…

We propose a first step toward multilingual end-to-end automatic speech recognition (ASR) by integrating knowledge about speech articulators. The key idea is to leverage a rich set of fundamental units that can be defined "universally"…

The pre-trained multi-lingual XLSR model generalizes well for language identification after fine-tuning on unseen languages. However, the performance significantly degrades when the languages are not very distinct from each other, for…

Well-trained machine-learning models, which leverage large amounts of open-source software data, have now become an interesting approach to automating many software engineering tasks. Several SE tasks have all been subject to this approach,…

For easier communication, posting, or commenting on each others posts, people use their dialects. In Africa, various languages and dialects exist. However, they are still underrepresented and not fully exploited for analytical studies and…

Machine translation in low-resource language pairs faces significant challenges due to the scarcity of parallel corpora and linguistic resources. This study focuses on the case of English-Marathi language pairs, where existing datasets are…

Building automatic speech recognition (ASR) systems is a challenging task, especially for under-resourced languages that need to construct corpora nearly from scratch and lack sufficient training data. It has emerged that several African…

Modeling code-switched speech is an important problem in automatic speech recognition (ASR). Labeled code-switched data are rare, so monolingual data are often used to model code-switched speech. These monolingual data may be more closely…

Bangla is a language spoken by approximately 240 million native speakers and around 300 million people worldwide. Despite being the 5th largest spoken language in the world, Bangla is still a "low-resource" language, and existing pretrained…

Semi-supervised training (SST) is a common approach to leverage untranscribed/unlabeled speech data to improve automatic speech recognition performance in low-resource languages. However, if the available unlabeled speech is mismatched to…

Multilingual language models often perform unevenly across different languages due to limited generalization capabilities for some languages. This issue is significant because of the growing interest in making universal language models that…

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)…