Related papers: Arab Voices: Mapping Standard and Dialectal Arabic…

Limited diversity in standardized benchmarks for evaluating audio representation learning (ARL) methods may hinder systematic comparison of current methods' capabilities. We present ARCH, a comprehensive benchmark for evaluating ARL methods…

The performance of learning models heavily relies on the availability and adequacy of training data. To address the dataset adequacy issue, researchers have extensively explored data augmentation (DA) as a promising approach. DA generates…

One of the major parts of the voice recognition field is the choice of acoustic features which have to be robust against the variability of the speech signal, mismatched conditions, and noisy environments. Thus, different speech feature…

This paper introduces the RGB Arabic Alphabet Sign Language (AASL) dataset. AASL comprises 7,856 raw and fully labelled RGB images of the Arabic sign language alphabets, which to our best knowledge is the first publicly available RGB…

Whisper, the recently developed multilingual weakly supervised model, is reported to perform well on multiple speech recognition benchmarks in both monolingual and multilingual settings. However, it is not clear how Whisper would fare under…

Automatic text-based diacritic restoration models generally have high diacritic error rates when applied to speech transcripts as a result of domain and style shifts in spoken language. In this work, we explore the possibility of improving…

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…

Although Germany has a diverse landscape of dialects, they are underrepresented in current automatic speech recognition (ASR) research. To enable studies of how robust models are towards dialectal variation, we present Betthupferl, an…

We present ArTST, a pre-trained Arabic text and speech transformer for supporting open-source speech technologies for the Arabic language. The model architecture follows the unified-modal framework, SpeechT5, that was recently released for…

Arabic dialect recognition presents a significant challenge in speech technology due to the linguistic diversity of Arabic and the scarcity of large annotated datasets, particularly for underrepresented dialects. This research investigates…

Pashto is spoken by approximately 60--80 million people but has no published benchmarks for multilingual automatic speech recognition (ASR) on any shared public test set. This paper reports the first reproducible multi-model evaluation on…

A sufficient amount of annotated data is usually required to fine-tune pre-trained language models for downstream tasks. Unfortunately, attaining labeled data can be costly, especially for multiple language varieties and dialects. We…

This work presents an extensive and detailed study on Audio-Visual Speech Recognition (AVSR) for five widely spoken languages: Chinese, Spanish, English, Arabic, and French. We have collected large-scale datasets for each language except…

The performance of automated speech recognition (ASR) systems is well known to differ for varied application domains. At the same time, vendors and research groups typically report ASR quality results either for limited use simplistic…

Zero-shot multi-speaker text-to-speech (ZS-TTS) systems have advanced for English, however, it still lags behind due to insufficient resources. We address this gap for Arabic, a language of more than 450 million native speakers, by first…

The growing importance of culturally-aware natural language processing systems has led to an increasing demand for resources that capture sociopragmatic phenomena across diverse languages. Nevertheless, Arabic-language resources for…

Large language models (LLMs) for Arabic are still dominated by Modern Standard Arabic (MSA), with limited support for Saudi dialects such as Najdi and Hijazi. This underrepresentation hinders their ability to capture authentic dialectal…

Voice based applications are ruling over the era of automation because speech has a lot of factors that determine a speakers information as well as speech. Modern Automatic Speech Recognition (ASR) is a blessing in the field of…

Automatic speech recognition (ASR) systems have been shown to have large quality disparities between the language varieties they are intended or expected to recognize. One way to mitigate this is to train or fine-tune models with more…

Automatic speech recognition (ASR) systems have achieved near-human accuracy on curated benchmarks, yet still fail in real-world voice agents under conditions that current evaluations do not systematically cover. Without diagnostic tools…