Anew wave of startups are using deep learning to build synthetic (合成的) voice act-组卷网

阅读理解-阅读单选 0.65 引用2 组卷94

A new wave of startups are using deep learning to build synthetic (合成的) voice actors for digital assistants, video-game characters, and corporate videos. Each one is based on a real voice actor, whose likeness has been preserved using AI. Companies can now license these voices to say whatever they need. They simply feed some text into the voice engine, and out will generate an audio clip of a natural-sounding performance.

Not too long ago, such deepfake voices had something of a bad reputation for their use in internet trickery. But their improving quality has since aroused the interest of a growing number of companies. Recent breakthroughs in deep learning have made it possible to replicate (仿制) many of the subtleties (细微差别) of human speech. These voices pause and breathe in all the right places. They can change their style or emotion. AI voices are also cheap and easy to work with. Unlike a recording of a human voice actor, synthetic voices can update their script (剧本) in real time. Some Al firms can now handle the voices for adapting ads depending on who is listening, changing not just the accent of the voice but also the words being spoken.

But there are limitations to how far AI can go. It’s still difficult to maintain the realism of a voice over long stretches of time that might be required for an audio book. And there’s little ability to control an AI voice’ s performance in the same way a director can guide a human performer. Expressive, creative and long-form projects are still best done by humans.

According to Rupal Patel, a professor at Northeastern University, the point of AI voices is ultimately not to replace existing audio work. The promise of AI voices is that they could open up entirely new possibilities.

【小题1】What plays a key role in the improvement of synthetic voices?

A．Licensing real voices.

B．Breakthroughs in deep learning.

C．Feeding texts into the voice engine.

D．Preserving the likeness of a real voice.

【小题2】Which can best describe AI voices?

A．Cheap and limitless.

B．Creative and irreplaceable.

C．Portable and ready to update.

D．Adaptable and easy to operate.

【小题3】In which of the following do AI voices perform best?

A．A TV talk show.