Related papers: Ara-Best-RQ: Multi Dialectal Arabic SSL

Recent advances in automatic speech recognition (ASR) have achieved accuracy levels comparable to human transcribers, which led researchers to debate if the machine has reached human performance. Previous work focused on the English…

We aim at improving spoken language modeling (LM) using very large amount of automatically transcribed speech. We leverage the INA (French National Audiovisual Institute) collection and obtain 19GB of text after applying ASR on 350,000…

This report introduces Dolphin, a large-scale multilingual automatic speech recognition (ASR) model that extends the Whisper architecture to support a wider range of languages. Our approach integrates in-house proprietary and open-source…

Large Language Models (LLMs) are increasingly used to answer everyday questions, yet their performance on culturally grounded and dialectal content remains uneven across languages. We propose a comprehensive method that (i) translates…

We present an analysis of diacritic recognition performance in Arabic Automatic Speech Recognition (ASR) systems. As most existing Arabic speech corpora do not contain all diacritical marks, which represent short vowels and other phonetic…

Large Language Models (LLMs) are becoming increasingly multilingual, supporting hundreds of languages, especially high resource ones. Unfortunately, Dialect variations are still underrepresented due to limited data and linguistic variation.…

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,…

Self-supervised learning (SSL) has been dramatically successful not only in monolingual but also in cross-lingual settings. However, since the two settings have been studied individually in general, there has been little research focusing…

Training a conventional automatic speech recognition (ASR) system to support multiple languages is challenging because the sub-word unit, lexicon and word inventories are typically language specific. In contrast, sequence-to-sequence models…

Existing Self-Supervised Learning (SSL) models for speech typically process speech signals at a fixed resolution of 20 milliseconds. This approach overlooks the varying informational content present at different resolutions in speech…

This paper presents XLS-R, a large-scale model for cross-lingual speech representation learning based on wav2vec 2.0. We train models with up to 2B parameters on nearly half a million hours of publicly available speech audio in 128…

We present ADI-20, an extension of the previously published ADI-17 Arabic Dialect Identification (ADI) dataset. ADI-20 covers all Arabic-speaking countries' dialects. It comprises 3,556 hours from 19 Arabic dialects in addition to Modern…

In Natural Language Processing (NLP), one of the most important tasks is text-to-SQL semantic parsing, which focuses on enabling users to interact with the database in a more natural manner. In recent years, text-to-SQL has made significant…

Code-switching -- the natural alternation between two languages within a single utterance -- remains one of the most challenging and under-studied conditions for automatic speech recognition (ASR). We present a benchmark evaluating five…

The use of multilingual language models for tasks in low and high-resource languages has been a success story in deep learning. In recent times, Arabic has been receiving widespread attention on account of its dialectal variance. While…

In recent years, self-supervised learning (SSL) has achieved tremendous success in various speech tasks due to its power to extract representations from massive unlabeled data. However, compared with tasks such as speech recognition (ASR),…

Thanks to the rise of self-supervised learning, automatic speech recognition (ASR) systems now achieve near-human performance on a wide variety of datasets. However, they still lack generalization capability and are not robust to domain…

Automatic Speech Recognition (ASR) transcripts, especially in low-resource languages like Bangla, contain a critical ambiguity: word-word repetitions can be either Repetition Disfluency (unintentional ASR error/hesitation) or Morphological…

In this work, we study the features extracted by English self-supervised learning (SSL) models in cross-lingual contexts and propose a new metric to predict the quality of feature representations. Using automatic speech recognition (ASR) as…

Recently, large pre-trained multilingual speech models have shown potential in scaling Automatic Speech Recognition (ASR) to many low-resource languages. Some of these models employ language adapters in their formulation, which helps to…