Related papers: Sequence-based Multi-lingual Low Resource Speech R…

End-to-end speech recognition systems usually require huge amounts of labeling resource, while annotating the speech data is complicated and expensive. Active learning is the solution by selecting the most valuable samples for annotation.…

Adapting large language models (LLMs) to new languages typically involves continual pre-training (CT) followed by supervised fine-tuning (SFT). However, this CT-then-SFT approach struggles with limited data in the context of low-resource…

Sentence-level embedding is essential for various tasks that require understanding natural language. Many studies have explored such embeddings for high-resource languages like English. However, low-resource languages like Bengali (a…

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…

In recent years, end-to-end speech recognition has emerged as a technology that integrates the acoustic, pronunciation dictionary, and language model components of the traditional Automatic Speech Recognition model. It is possible to…

The difficulty of acquiring abundant, high-quality data, especially in multi-lingual contexts, has sparked interest in addressing low-resource scenarios. Moreover, current literature rely on fixed expressions from language IDs, which…

Multilingual end-to-end(E2E) models have shown a great potential in the expansion of the language coverage in the realm of automatic speech recognition(ASR). In this paper, we aim to enhance the multilingual ASR performance in two ways,…

Recently, end-to-end models have become a popular approach as an alternative to traditional hybrid models in automatic speech recognition (ASR). The multi-speaker speech separation and recognition task is a central task in cocktail party…

In this work, we explore the benefits of using multilingual bottleneck features (mBNF) in acoustic modelling for the automatic speech recognition of code-switched (CS) speech in African languages. The unavailability of annotated corpora in…

The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…

We introduce an approach to multilingual speech synthesis which uses the meta-learning concept of contextual parameter generation and produces natural-sounding multilingual speech using more languages and less training data than previous…

Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute --…

The rapid growth of voice assistants powered by large language models (LLM) has highlighted a need for speech instruction data to train these systems. Despite the abundance of speech recognition data, there is a notable scarcity of speech…

The longstanding goal of multi-lingual learning has been to develop a universal cross-lingual model that can withstand the changes in multi-lingual data distributions. There has been a large amount of work to adapt such multi-lingual models…

Large language models (LLMs) have achieved state-of-the-art performance in various software engineering tasks, including error detection, clone detection, and code translation, primarily leveraging high-resource programming languages like…

Word order variances generally exist in different languages. In this paper, we hypothesize that cross-lingual models that fit into the word order of the source language might fail to handle target languages. To verify this hypothesis, we…

Segmental conditional random fields (SCRFs) and connectionist temporal classification (CTC) are two sequence labeling methods used for end-to-end training of speech recognition models. Both models define a transcription probability by…

Multilingual language models have been a crucial breakthrough as they considerably reduce the need of data for under-resourced languages. Nevertheless, the superiority of language-specific models has already been proven for languages having…

This work explores better adaptation methods to low-resource languages using an external language model (LM) under the framework of transfer learning. We first build a language-independent ASR system in a unified sequence-to-sequence (S2S)…

Best-performing speech models are trained on large amounts of data in the language they are meant to work for. However, most languages have sparse data, making training models challenging. This shortage of data is even more prevalent in…