Related papers: QVoice: Arabic Speech Pronunciation Learning Appli…

We observe a recent behaviour on social media, in which users intentionally remove consonantal dots from Arabic letters, in order to bypass content-classification algorithms. Content classification is typically done by fine-tuning…

Self-supervised learning (SSL) approaches such as wav2vec 2.0 and HuBERT models have shown promising results in various downstream tasks in the speech community. In particular, speech representations learned by SSL models have been shown to…

Sign language is an essential means of communication for millions of people around the world and serves as their primary language. However, most communication tools are developed for spoken and written languages which can cause problems and…

Speech synthesis is the artificial production of human speech. A typical text-to-speech system converts a language text into a waveform. There exist many English TTS systems that produce mature, natural, and human-like speech synthesizers.…

This paper proposes a sequence-to-sequence learning approach for Arabic pronoun resolution, which explores the effectiveness of using advanced natural language processing (NLP) techniques, specifically Bi-LSTM and the BERT pre-trained…

We introduce SimplerVoice: a key message and visual description generator system to help low-literate adults navigate the information-dense world with confidence, on their own. SimplerVoice can automatically generate sensible sentences…

Audio-visual speaker extraction has attracted increasing attention, as it removes the need for pre-registered speech and leverages the visual modality as a complement to audio. Although existing methods have achieved impressive performance,…

Vector Quantized Variational AutoEncoders (VQ-VAE) are a powerful representation learning framework that can discover discrete groups of features from a speech signal without supervision. Until now, the VQ-VAE architecture has previously…

Lipreading involves using visual data to recognize spoken words by analyzing the movements of the lips and surrounding area. It is a hot research topic with many potential applications, such as human-machine interaction and enhancing audio…

The goal of voice conversion is to transform the speech of a source speaker to sound like that of a reference speaker while preserving the original content. A key challenge is to extract disentangled linguistic content from the source and…

Unsupervised representation learning of speech has been of keen interest in recent years, which is for example evident in the wide interest of the ZeroSpeech challenges. This work presents a new method for learning frame level…

Grammatical Error Correction (GEC) is an important aspect of natural language processing. Arabic has a complicated morphological and syntactic structure, posing a greater challenge than other languages. Even though modern neural models have…

This paper presents a novel approach to fine-tuning the Qwen2-1.5B model for Arabic language processing using Quantized Low-Rank Adaptation (QLoRA) on a system with only 4GB VRAM. We detail the process of adapting this large language model…

Parsing the Arabic language is a difficult task given the specificities of this language and given the scarcity of digital resources (grammars and annotated corpora). In this paper, we suggest a method for Arabic parsing based on supervised…

This paper addresses the challenge of learning to recite the Quran for non-Arabic speakers. We explore the possibility of crowdsourcing a carefully annotated Quranic dataset, on top of which AI models can be built to simplify the learning…

The focus of language model evaluation has transitioned towards reasoning and knowledge-intensive tasks, driven by advancements in pretraining large models. While state-of-the-art models are partially trained on large Arabic texts,…

The proposed model aims to develop a speech recognition technology for hearing, speech, or cognitively disabled people. All the available technology in the field of speech recognition doesn't come with an interface for communication for…

Conversational systems rely heavily on speech recognition to interpret and respond to user commands and queries. Despite progress on speech recognition accuracy, errors may still sometimes occur and can significantly affect the end-user…

Zero-shot ASR for Arabic remains challenging: while multilingual models perform well on Modern Standard Arabic (MSA), error rates rise sharply on dialectal and accented speech due to linguistic mismatch and scarce labeled data. We study…

The lack of labeled second language (L2) speech data is a major challenge in designing mispronunciation detection models. We introduce SpeechBlender - a fine-grained data augmentation pipeline for generating mispronunciation errors to…