In this paper we present the creation of an Arabic version of Automated Speech Recognition System (ASR). This system is based on the open source Sphinx-4, from the Carnegie Mellon University. Which is a speech recognition system based on discrete hidden Markov models (HMMs). We investigate the changes that must be made to the model to adapt Arabic voice recognition.
Keywords: Speech recognition, Acoustic model, Arabic language, HMMs, CMUSphinx-4, Artificial intelligence.
UFR Informatique et Nouvelles Technologies d'Information et de Communication（信息与通信新技术学院）；Département de Mathématiques et Informatique, Faculté des Sciences（理学院数学与计算机科学系）；Carnegie Mellon University（卡内基梅隆大学）
In this paper Arabic was investigated from the speech recognition problem point of view. We propose a novel approach to build an Arabic Automated Speech Recognition System (ASR). This system is based on the open source CMU Sphinx-4, from the Carnegie Mellon University. CMU Sphinx is a large-vocabulary; speaker-independent, continuous speech recognition system based on discrete Hidden Markov Models (HMMs). We build a model using utilities from the OpenSource CMU Sphinx. We will demonstrate the possible adaptability of this system to Arabic voice recognition.
This paper presents the continuation of the work completed by Satori and all. [SCH07] by the realization of an automatic speech recognition system (ASR) for Arabic language based SPHINX 4 system. The previous work was limited to the recognition of the first ten digits, whereas the present work is a remarkable projection consisting in continuous Arabic speech recognition with a rate of recognition of surroundings 96%.
Higher School of Science and Technology of Tunis（突尼斯高等科学技术学院）
This work consists of creating a system of the Computer Assisted Language Learning (CALL) based on a system of Automatic Speech Recognition (ASR) for the Arabic language using the tool CMU Sphinx3 [1], based on the approach of HMM. To this work, we have constructed a corpus of six hours of speech recordings with a number of nine speakers. we find in the robustness to noise a grounds for the choice of the HMM approach [2]. the results achieved are encouraging since our corpus is made by only nine speakers, but they are always reasons that open the door for other improvement works.
Speech translation (ST) is the task of directly translating acoustic speech signals in a source language into text in a foreign language. ST task has been addressed, for a long time, using a pipeline approach with two modules : first an Automatic Speech Recognition (ASR) in the source language followed by a text-to-text Machine translation (MT). In the past few years, we have seen a paradigm shift towards the end-to-end approaches using sequence-to-sequence deep neural network models. This paper presents our efforts towards the development of the first Broadcast News end-to-end Arabic to Engli…
Qatar Computing Research Institute, HBKU（哈马德·本·哈利法大学卡塔尔计算研究所）；University of Edinburgh（爱丁堡大学）
This paper describes the Arabic MGB-3 Challenge - Arabic Speech Recognition in the Wild. Unlike last year's Arabic MGB-2 Challenge, for which the recognition task was based on more than 1,200 hours broadcast TV news recordings from Aljazeera Arabic TV programs, MGB-3 emphasises dialectal Arabic using a multi-genre collection of Egyptian YouTube videos. Seven genres were used for the data collection: comedy, cooking, family/kids, fashion, drama, sports, and science (TEDx). A total of 16 hours of videos, split evenly across the different genres, were divided into adaptation, development and eval…
ZAEBUC-Spoken: A Multilingual Multidialectal Arabic-English Speech Corpus
New York University Abu Dhabi（纽约大学阿布扎比分校）；University of Stuttgart（斯图加特大学）；University of Tübingen（蒂宾根大学）；United Arab Emirates University（阿联酋大学）；Zayed University（扎耶德大学）
Qatar Computing Research Institute, HBKU（哈马德·本·哈利法大学卡塔尔计算研究所）；MIT Computer Science and Artificial Intelligence Laboratory (CSAIL)（麻省理工学院计算机科学与人工智能实验室）；JHU Center for Language and Speech Processing (CLSP)（约翰斯·霍普金斯大学语言与语音处理中心）；University of Edinburgh（爱丁堡大学）
We investigate different approaches for dialect identification in Arabic broadcast speech, using phonetic, lexical features obtained from a speech recognition system, and acoustic features using the i-vector framework. We studied both generative and discriminate classifiers, and we combined these features using a multi-class Support Vector Machine (SVM). We validated our results on an Arabic/English language identification task, with an accuracy of 100%. We used these features in a binary classifier to discriminate between Modern Standard Arabic (MSA) and Dialectal Arabic, with an accuracy of …
Almieyar: A Culturally Grounded Benchmark for Multi-Dialect Arabic Speech Recognition
QCRI, HBKU（卡塔尔计算研究所，哈马德·本·哈利法大学）；Qatar University（卡塔尔大学）；UDST（多哈科技大学）；Algo AI；UCL（伦敦大学学院）；University of Tripoli（的黎波里大学）；AUC（开罗美国大学）；KAUST（阿卜杜拉国王科技大学）；CMU-Q（卡内基梅隆大学卡塔尔分校）；KFUPM（法赫德国王石油与矿产大学）；Alfaisal University（费萨尔大学）；Damascus University（大马士革大学）；Princeton University（普林斯顿大学）；ENSIAS, Mohammed V University（穆罕默德五世大学国家计算机科学与系统分析学院）；Sultan Qaboos University（苏丹卡布斯大学）；DFKI（德国人工智能研究中心）；University of Waterloo（滑铁卢大学）；USTHB（阿尔及尔科技大学）
This work is part of a large research project entitled "Oréodule" aimed at developing tools for automatic speech recognition, translation, and synthesis for Arabic language. Our attention has mainly been focused on an attempt to improve the probabilistic model on which our semantic decoder is based. To achieve this goal, we have decided to test the influence of the pertinent context use, and of the contextual data integration of different types, on the effectiveness of the semantic decoder. The findings are quite satisfactory.
NADI 2026: The Second Multidialectal Arabic Speech Processing Shared Task
The University of British Columbia（不列颠哥伦比亚大学）；King Fahd University of Petroleum & Minerals（法赫德国王石油与矿业大学）；Avignon Université（阿维尼翁大学）；ELYADATA（ELYADATA公司）；King Abdullah University of Science & Technology（阿卜杜拉国王科技大学）；NYU Abu Dhabi（纽约大学阿布扎比分校）
Munsit at NADI 2025 Shared Task 2: Pushing the Boundaries of Multidialectal Arabic ASR with Weakly Supervised Pretraining and Continual Supervised Fine-tuning
University of Stuttgart（斯图加特大学）；Raisa Energy LLC（Raisa Energy 有限责任公司）；The German University in Cairo（开罗德国大学）
Code-switching (CS), defined as the mixing of languages in conversations, has become a worldwide phenomenon. The prevalence of CS has been recently met with a growing demand and interest to build CS ASR systems. In this paper, we present our work on code-switched Egyptian Arabic-English automatic speech recognition (ASR). We first contribute in filling the huge gap in resources by collecting, analyzing and publishing our spontaneous CS Egyptian Arabic-English speech corpus. We build our ASR systems using DNN-based hybrid and Transformer-based end-to-end models. In this paper, we present a thor…
Towards stable AI systems for Evaluating Arabic Pronunciations
Bio-Medical Imaging Core, Core Technology Platforms, New York University Abu Dhabi（生物医学成像核心、核心技术平台、纽约大学阿布扎比分校）；Institut de recherche technologique SystemX（SystemX技术研究所）；NYUAD Research Institute, New York University Abu Dhabi（NYUAD研究学院、纽约大学阿布扎比分校）；Courant Institute of Mathematical Sciences, New York University（Courant数学科学研究所、纽约大学）
Casablanca: Data and Models for Multidialectal Arabic Speech Recognition
University of British Columbia（不列颠哥伦比亚大学）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；INSEA（国家统计与应用经济学院）；Ain Shams Univ.（艾因夏姆斯大学）；Technische Hochschule Mittelhessen（中黑森应用技术大学）；UM6P（穆罕默德六世大学）；ESI（国家工程学校）；Université de Nouakchott（努瓦克肖特大学）；Birzeit University（比尔宰特大学）；JUST（约旦科技大学）；TEK-UP；Cairo University（开罗大学）；Invertible AI（可逆人工智能公司）
NADI 2025: The First Multidialectal Arabic Speech Processing Shared Task
The University of British Columbia（不列颠哥伦比亚大学）；Hamad Bin Khalifa University（哈马德·本·卡伊夫大学）；Birzeit University（伯莱兹大学）；MBZUAI（穆罕默德·本·拉希德智能科学与技术研究院）；NYU Abu Dhabi（纽约大学阿布扎克分校）
HBKU（哈马德·本·哈利法大学）；Qatar Computing Research Institute（卡塔尔计算研究所）；Kanari AI（卡纳里人工智能公司）；Carnegie Mellon University（卡内基梅隆大学）
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 language and modular hidden Markov model-deep neural network (HMM-DNN) systems. In this paper, we perform a comprehensive benchmarking for end-to-end transformer ASR, modular HMM-DNN ASR, and human speech recognition (HSR) on the Arabic language and its dialects. For the HSR, we evaluate linguist performance and lay-native speaker performance on a new dataset colle…
Qatar Computing Research Institute, HBKU（卡塔尔计算研究所，哈马德·本·哈利法大学）；Kanari AI；University of Helwan（赫勒万大学）
Code-switching in automatic speech recognition (ASR) is an important challenge due to globalization. Recent research in multilingual ASR shows potential improvement over monolingual systems. We study key issues related to multilingual modeling for ASR through a series of large-scale ASR experiments. Our innovative framework deploys a multi-graph approach in the weighted finite state transducers (WFST) framework. We compare our WFST decoding strategies with a transformer sequence to sequence system trained on the same data. Given a code-switching scenario between Arabic and English languages, o…
KANARI AI（卡纳里人工智能公司）；Johns Hopkins University（约翰斯·霍普金斯大学）；Qatar Computing Research Institute（卡塔尔计算研究所）
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 structure complexity, and domain mismatch. The most common method for addressing CS is to train an ASR system with the available transcribed CS speech, along with monolingual data. In this work, we propose a zero-shot learning methodology for CS-ASR by augmenting the monolingual data with artificially generating CS text. We based our approach on random lexical repl…
MIT Computer Science and Artificial Intelligence Laboratory (CSAIL)（麻省理工学院计算机科学与人工智能实验室）；Qatar Computing Research Institute, HBKU（哈马德·本·哈利法大学卡塔尔计算研究所）
In order to successfully annotate the Arabic speech con- tent found in open-domain media broadcasts, it is essential to be able to process a diverse set of Arabic dialects. For the 2017 Multi-Genre Broadcast challenge (MGB-3) there were two possible tasks: Arabic speech recognition, and Arabic Dialect Identification (ADI). In this paper, we describe our efforts to create an ADI system for the MGB-3 challenge, with the goal of distinguishing amongst four major Arabic dialects, as well as Modern Standard Arabic. Our research fo- cused on dialect variability and domain mismatches between the trai…
Leveraging Data Collection and Unsupervised Learning for Code-switched Tunisian Arabic Automatic Speech Recognition
Tunis Business School（突尼斯商学院）；University of Michigan-Dearborn（密歇根大学迪尔伯恩分校）；Abshore；LTCI, Télécom Paris, Institut Polytechnique de Paris（巴黎理工学院巴黎电信学院LTCI）
Overcoming Data Scarcity in Multi-Dialectal Arabic ASR via Whisper Fine-Tuning
Department of Internal Medicine, Division of Nephrology（内科学部，肾病科）；Bernoulli Institute for Mathematics, Computer Science（伯努利数学、计算机科学研究所）；Speech Technology Lab, Campus Fryslân（语音技术实验室，弗里西恩校区）
Deep learning mechanisms are prevailing approaches in recent days for the various tasks in natural language processing, speech recognition, image processing and many others. To leverage this we use deep learning based mechanism specifically Bidirectional- Long Short-Term Memory (B-LSTM) for the task of dialectic identification in Arabic and German broadcast speech and Long Short-Term Memory (LSTM) for discriminating between similar Languages. Two unique B-LSTM models are created using the Large-vocabulary Continuous Speech Recognition (LVCSR) based lexical features and a fixed length of 400 pe…
KANARI AI（卡纳里人工智能公司）；Carnegie Mellon University（卡内基梅隆大学）；Qatar Computing Research Institute, HBKU（哈马德·本·哈利法大学卡塔尔计算研究所）；Nagoya University（名古屋大学）；Human Dataware Lab. Co., Ltd.（人类数据仓库实验室有限公司）；American University of Beirut（贝鲁特美国大学）
Several high-resource Text to Speech (TTS) systems currently produce natural, well-established human-like speech. In contrast, low-resource languages, including Arabic, have very limited TTS systems due to the lack of resources. We propose a fully unsupervised method for building TTS, including automatic data selection and pre-training/fine-tuning strategies for TTS training, using broadcast news as a case study. We show how careful selection of data, yet smaller amounts, can improve the efficiency of TTS system in generating more natural speech than a system trained on a bigger dataset. We ad…
Tsinghua University（清华大学）；Chinese Academy of Sciences（中国科学院）；SpeechOcean（海天瑞声）
We present the OC16-CE80 Chinese-English mixlingual speech database which was released as a main resource for training, development and test for the Chinese-English mixlingual speech recognition (MixASR-CHEN) challenge on O-COCOSDA 2016. This database consists of 80 hours of speech signals recorded from more than 1,400 speakers, where the utterances are in Chinese but each involves one or several English words. Based on the database and another two free data resources (THCHS30 and the CMU dictionary), a speech recognition (ASR) baseline was constructed with the deep neural network-hidden Marko…
We present an experimental dataset, Basic Dataset for Sorani Kurdish Automatic Speech Recognition (BD-4SK-ASR), which we used in the first attempt in developing an automatic speech recognition for Sorani Kurdish. The objective of the project was to develop a system that automatically could recognize simple sentences based on the vocabulary which is used in grades one to three of the primary schools in the Kurdistan Region of Iraq. We used CMUSphinx as our experimental environment. We developed a dataset to train the system. The dataset is publicly available for non-commercial use under the CC …
Most recent speech recognition models rely on large supervised datasets, which are unavailable for many low-resource languages. In this work, we present a speech recognition pipeline that does not require any audio for the target language. The only assumption is that we have access to raw text datasets or a set of n-gram statistics. Our speech pipeline consists of three components: acoustic, pronunciation, and language models. Unlike the standard pipeline, our acoustic and pronunciation models use multilingual models without any supervision. The language model is built using n-gram statistics …
Qatar Computing Research Institute（卡塔尔计算研究所）；KanarI AI
With the advent of globalization, there is an increasing demand for multilingual automatic speech recognition (ASR), handling language and dialectal variation of spoken content. Recent studies show its efficacy over monolingual systems. In this study, we design a large multilingual end-to-end ASR using self-attention based conformer architecture. We trained the system using Arabic (Ar), English (En) and French (Fr) languages. We evaluate the system performance handling: (i) monolingual (Ar, En and Fr); (ii) multi-dialectal (Modern Standard Arabic, along with dialectal variation such as Egyptia…
