Text-to-Speech | TTS | Speech Synthesis

Text-to-Speech is about converting texts into a human voice. You type the texts, and the technology converts your texts into a human voice.

In a multi-cultural multilingual environment like Hong Kong, people often mix English words with Cantonese or Chinese words when they speak.  Some English words are so common in daily conversations that even native speakers would not remember the Cantonese or Chinese equivalent.  Even if the text contains both Chinese and English characters, multilingual text-to-speech speaks both languages in the SAME natural human voice.  Click here for demo.

Text-to-speech has been commercialized by MIT technologists since the 1980s.  However, the voice has been robotic, making it suitable for limited and special applications only.  More recently, great strides have been made in the areas of artificial intelligence and machine learning.  The combination of such technological advances and decades of speech knowledge completely revolutionizes the text-to-speech industry.  Today, you can hardly hear the difference between the voices of the human and text-to-speech.  Click here for demo.

As a tonal language, Chinese adds an extra layer of hurdle for speech technologists to overcome.  Being more like a verbal language than a written language, Cantonese raises the bar even higher.  The complex interaction between its intonation, idiosyncrasy, and colloquialism makes the development of Cantonese text-to-speech difficult for many technologists.  However, committed to Hong Kong, InfoTalk has developed the world’s best Cantonese text-to-speech.  Click here for demo.

Text-to-speech has always been a multi-disciplinary discipline involving computer science, engineering, signal processing, acoustics, language, and linguistics, among others.  With recent technology advances in artificial intelligence (AI), machine learning (ML), and deep neural networks (DNN), text-to-speech has become more interdisciplinary than ever before.

Text-to-speech technology in Cantonese, Putonghua, and English have been successfully deployed in a wide variety of systems and industries in Hong Kong and Asia.  Successful commercial deployment of text-to-speech technology, especially in mission-critical high-traffic applications for public use, requires experience, expertise, and knowhow that are above and beyond simplistic laboratory experiments.

There are other names for text-to-speech (TTS), such as text-to-voice, speech synthesis, and voice synthesis. Chinese and Cantonese names in Hong Kong, China, and Asia include 文語轉換, 文字轉語音, 語音合成. They all mean more or less the same technology. From our perspective, Cantonese text-to-speech is the same as Cantonese speech synthesis, and Chinese text-to-speech is the same as Chinese speech synthesis. However, Hong Kong text-to-speech (or Hong Kong speech synthesis) is unique in that people speaking Cantonese often mix it with English. Thus, text-to-speech in Hong Kong (or speech synthesis in Hong Kong) speaks Cantonese mixed with English. The same applies to Putonghua/Mandarin text-to-speech or Putonghua/Mandarin speech synthesis.