Related papers: Dialectal Coverage And Generalization in Arabic Sp…
This survey offers a comprehensive overview of Large Language Models (LLMs) designed for Arabic language and its dialects. It covers key architectures, including encoder-only, decoder-only, and encoder-decoder models, along with the…
Current automatic speech recognition (ASR) models are designed to be used across many languages and tasks without substantial changes. However, this broad language coverage hides performance gaps within languages, for example, across…
Arabic dialect identification is a specific task of natural language processing, aiming to automatically predict the Arabic dialect of a given text. Arabic dialect identification is the first step in various natural language processing…
The pervasiveness of intra-utterance code-switching (CS) in spoken content requires that speech recognition (ASR) systems handle mixed language. Designing a CS-ASR system has many challenges, mainly due to data scarcity, grammatical…
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…
Arabic dialect identification (ADI) systems are essential for large-scale data collection pipelines that enable the development of inclusive speech technologies for Arabic language varieties. However, the reliability of current ADI systems…
There is a significant gap in evaluating cultural reasoning in LLMs using conversational datasets that capture culturally rich and dialectal contexts. Most Arabic benchmarks focus on short text snippets in Modern Standard Arabic (MSA),…
Multi-speaker automatic speech recognition (ASR) is crucial for many real-world applications, but it requires dedicated modeling techniques. Existing approaches can be divided into modular and end-to-end methods. Modular approaches separate…
Question answering (QA) systems are now available through numerous commercial applications for a wide variety of domains, serving millions of users that interact with them via speech interfaces. However, current benchmarks in QA research do…
Arabic is a Semitic language which is widely spoken with many dialects. Given the success of pre-trained language models, many transformer models trained on Arabic and its dialects have surfaced. While these models have been compared with…
Multi-speaker automatic speech recognition (MS-ASR) faces significant challenges in transcribing overlapped speech, a task critical for applications like meeting transcription and conversational analysis. While serialized output training…
Automatic Speech Recognition (ASR) technology has witnessed significant advancements in recent years, revolutionizing human-computer interactions. While major languages have benefited from these developments, lesser-resourced languages like…
Discrete speech representations have garnered recent attention for their efficacy in training transformer-based models for various speech-related tasks such as automatic speech recognition (ASR), translation, speaker verification, and joint…
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…
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,…
Language in the Arab world presents a complex diglossic and multilingual setting, involving the use of Modern Standard Arabic, various dialects and sub-dialects, as well as multiple European languages. This diverse linguistic landscape has…
Recent advances in speech-enabled AI, including Google's NotebookLM and OpenAI's speech-to-speech API, are driving widespread interest in voice interfaces globally. Despite this momentum, there exists no publicly available…
Automatic Speech Recognition (ASR) can play a crucial role in enhancing the accessibility of spoken languages worldwide. In this paper, we build a set of ASR tools for Amharic, a language spoken by more than 50 million people primarily in…
Ramsa is a developing 41-hour speech corpus of Emirati Arabic designed to support sociolinguistic research and low-resource language technologies. It contains recordings from structured interviews with native speakers and episodes from…
Automatic speech recognition (ASR) has benefited from advances in pretrained speech and language models, yet most systems remain constrained to monolingual settings and short, isolated utterances. While recent efforts in context-aware ASR…