Advancements in Arabic Text-to-Speech Systems: A 22-Year Literature Review

Chemnad, Khansa; Othman, Achraf

doi:10.1109/access.2023.3260844

Cited by 4 publications

(2 citation statements)

References 108 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Arabic language, a linguistic tapestry rich in history and cultural significance, is one of the most widely spoken languages globally, boasting over 420 million speakers with it as their first language [1,2]. It is the official language in more than 22 countries, underscoring its geopolitical importance [3]. Additionally, Arabic is one of the six official languages of the United Nations (UN), highlighting its essential role in international diplomacy and communication [4].…”

Section: Introduction 1arabic Language Challengesmentioning

confidence: 99%

AI-Generated Text Detector for Arabic Language Using Encoder-Based Transformer Architecture

Alshammari,

El-Sayed,

Elleithy

2024

BDCC

View full text Add to dashboard Cite

The effectiveness of existing AI detectors is notably hampered when processing Arabic texts. This study introduces a novel AI text classifier designed specifically for Arabic, tackling the distinct challenges inherent in processing this language. A particular focus is placed on accurately recognizing human-written texts (HWTs), an area where existing AI detectors have demonstrated significant limitations. To achieve this goal, this paper utilized and fine-tuned two Transformer-based models, AraELECTRA and XLM-R, by training them on two distinct datasets: a large dataset comprising 43,958 examples and a custom dataset with 3078 examples that contain HWT and AI-generated texts (AIGTs) from various sources, including ChatGPT 3.5, ChatGPT-4, and BARD. The proposed architecture is adaptable to any language, but this work evaluates these models’ efficiency in recognizing HWTs versus AIGTs in Arabic as an example of Semitic languages. The performance of the proposed models has been compared against the two prominent existing AI detectors, GPTZero and OpenAI Text Classifier, particularly on the AIRABIC benchmark dataset. The results reveal that the proposed classifiers outperform both GPTZero and OpenAI Text Classifier with 81% accuracy compared to 63% and 50% for GPTZero and OpenAI Text Classifier, respectively. Furthermore, integrating a Dediacritization Layer prior to the classification model demonstrated a significant enhancement in the detection accuracy of both HWTs and AIGTs. This Dediacritization step markedly improved the classification accuracy, elevating it from 81% to as high as 99% and, in some instances, even achieving 100%.

show abstract

Section: Introduction 1arabic Language Challengesmentioning

confidence: 99%

AI-Generated Text Detector for Arabic Language Using Encoder-Based Transformer Architecture

Alshammari,

El-Sayed,

Elleithy

2024

BDCC

View full text Add to dashboard Cite

show abstract

“…Speech synthesis has gained great progress with the introduction of deep learning, and many advanced acoustic models and vocoders have emerged, which synthesize audio with far better quality than the previous traditional speech synthesis models [ 1 , 2 , 3 , 4 ]. Speech synthesis is a one-to-many mapping generation task that processes the input text to synthesize high-quality audio samples.…”

Section: Introductionmentioning

confidence: 99%

Research on Speech Synthesis Based on Mixture Alignment Mechanism

Deng,

Wu,

Qiu

et al. 2023

Sensors

View full text Add to dashboard Cite

In recent years, deep learning-based speech synthesis has attracted a lot of attention from the machine learning and speech communities. In this paper, we propose Mixture-TTS, a non-autoregressive speech synthesis model based on mixture alignment mechanism. Mixture-TTS aims to optimize the alignment information between text sequences and mel-spectrogram. Mixture-TTS uses a linguistic encoder based on soft phoneme-level alignment and hard word-level alignment approaches, which explicitly extract word-level semantic information, and introduce pitch and energy predictors to optimally predict the rhythmic information of the audio. Specifically, Mixture-TTS introduces a post-net based on a five-layer 1D convolution network to optimize the reconfiguration capability of the mel-spectrogram. We connect the output of the decoder to the post-net through the residual network. The mel-spectrogram is converted into the final audio by the HiFi-GAN vocoder. We evaluate the performance of the Mixture-TTS on the AISHELL3 and LJSpeech datasets. Experimental results show that Mixture-TTS is somewhat better in alignment information between the text sequences and mel-spectrogram, and is able to achieve high-quality audio. The ablation studies demonstrate that the structure of Mixture-TTS is effective.

show abstract

An end-to-end Tacotron model versus pre trained Tacotron model for Arabic text-to-speech synthesis

Mutawa

2023

Journal of Engineering Research

View full text Add to dashboard Cite

Advancements in Arabic Text-to-Speech Systems: A 22-Year Literature Review

Cited by 4 publications

References 108 publications

AI-Generated Text Detector for Arabic Language Using Encoder-Based Transformer Architecture

AI-Generated Text Detector for Arabic Language Using Encoder-Based Transformer Architecture

Research on Speech Synthesis Based on Mixture Alignment Mechanism

An end-to-end Tacotron model versus pre trained Tacotron model for Arabic text-to-speech synthesis

Contact Info

Product

Resources

About