Led by Shanghai Jiao Tong University’s X-LANCE Lab – one of China’s top audiovisual and language processing research entities – the model is named Habibi, meaning “my dear” in Arabic.
In presenting their findings, the research team spearheaded by Chen Yushen described the project in a paper as “the first open-source framework for unified-dialectal Arabic speech synthesis”.
“To the best of our knowledge, research on unified-dialectal Arabic TTS is absent, not to mention an open-source framework,” the authors said in the paper, “Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis”. It was published last month on arXiv, an open-access repository that is not peer-reviewed.
01:12
World’s first ‘fully biomimetic embodied intelligent robot’ debuts in Shanghai
World’s first ‘fully biomimetic embodied intelligent robot’ debuts in Shanghai
Habibi has the “zero-shot” ability, meaning the model can easily clone a voice by using just a short reference audio clip, without prior explicit or extensive training. This allows applications in highly efficient and on-the-fly scenarios.
United Arab Emirates, Arabic, South China Morning Post, Shanghai Jiao Tong University, Middle East, Abu Dhabi, Alibaba, text-to-speech, Habibi, China, ElevenLabs, Algeria, Morocco, Egypt, AI#Meet #Habibi #Chinese #uniting #Arabic #dialects #Middle #East1772259129
Abu Dhabi
ai
Algeria
alibaba
Arabic
China
Chinese
dialects
East
Egypt
ElevenLabs
Habibi
meet
Middle
Middle East
Morocco
Shanghai Jiao Tong University
South China Morning Post
text-to-speech
United Arab Emirates
uniting
