Thursday May 23, 2019
Home Lead Story Tech Giant Go...

Tech Giant Google Announces its First Speech-to-speech Translation System

Lately, Google has been working aggressively on its translation systems

0
//
google
FILE - A woman walks past the logo for Google at the China International Import Expo in Shanghai, Nov. 5, 2018. VOA

Google has announced its first direct speech-to-speech translation system called “Translatotron” that can convert verbal communication from one language to another while maintaining the speaker’s voice and tempo.

“Translatotron” is based on a sequence-to-sequence network which takes source spectrograms — a visual representation of frequencies — as input and generates spectrograms of the translated content in the target language, Ye Jia and Ron Weiss, software engineers at Google Artificial Intelligence (AI) wrote in a blog post on Wednesday.

The model makes use of two other separately trained components — a neural vocoder that converts output spectrograms to time-domain waveforms and a speaker encoder that can be used to maintain the character of the source speaker’s voice in the synthesised translated speech.

For now, the results of Google’s demonstration of the translation system lag behind a conventional cascade system, but the search engine giant said it has “demonstrated the feasibility of the end-to-end direct speech-to-speech translation”.

“By incorporating a speaker encoder network, ‘Translatotron’ is also able to retain the original speaker’s vocal characteristics in the translated speech, which makes the translated speech sound more natural and less jarring,” Jia and Weiss said.

google, online tracking
A man walks past a Google sign outside with a span of the Bay Bridge at rear in San Francisco, May 1, 2019. VOA

The company said that “Translatotron” is the first end-to-end model that can directly translate speech from one language into another.

“We hope that this work can serve as a starting point for future research on end-to-end speech-to-speech translation systems,” the blog-post noted.

Lately, Google has been working aggressively on its translation systems.

Also Read- Apple’s Plan to Introduce its own iPhone 5G Chip Could Take Time

Adding more languages to its real-time translation feature, earlier in 2018, the company introduced accents in Google Translate with a variety of languages in region-based pronunciations.

In February, Google extended the “Interpreter” mode on its Assistant to Home speakers and other third-party devices to help users have real-time conversations with compatible devices and translate them into 26 listed languages. (IANS)

Next Story

Google AI Can Now Predict Lung Cancer Accurately

The research was published in the journal Nature Medicine

0
Google, Main One, russia
A Google logo is displayed at the entrance to the internet based company's offices in Toronto. VOA

A team of Google researchers has used a deep-learning algorithm to detect lung cancer accurately from computed scans.

The work demonstrates the potential for Artificial Intelligence (AI) to increase both accuracy and consistency, which could help accelerate adoption of lung cancer screening worldwide.

Lung cancer is the deadliest of all cancers worldwide — more than breast, prostate, and colorectal cancers combined — and it’s the sixth most common cause of death globally, according to the World Health Organization.

“Using advances in 3D volumetric modeling alongside datasets from our partners (including Northwestern University), we’ve made progress in modeling lung cancer prediction as well as laying the groundwork for future clinical testing,” Shravya Shetty, M.S. Technical Lead at Google explained in a blog post late Monday.

Google researchers created a model that can not only generate the overall lung cancer malignancy prediction (viewed in 3D volume) but also identify subtle malignant tissue in the lungs (lung nodules).

Google on an Android device. Pixabay

In the research, Google AI leveraged 45,856 de-identified chest CT screening cases (some in which cancer was found).

“When using a single CT scan for diagnosis, our model performed on par or better than the six radiologists. We detected five per cent more cancer cases while reducing false-positive exams by more than 11 per cent compared to unassisted radiologists in our study,” said Google.

For an asymptomatic patient with no history of cancer, the AI system reviewed and detected potential lung cancer that had been previously called normal.

Also Read- Apple to Substitute Watch Series 3 Repairs with Series 4: Report

These initial results are encouraging, but further studies will assess the impact and utility in clinical practice, said Google.

The research was published in the journal Nature Medicine. (IANS)