AT&T Labs will start selling speech software that it says is so good at reproducing the sounds, inflections and intonations of a human voice that it can re-create voices and even bring the voices of long-dead celebrities back to life.
The software, which turns printed text into synthesized speech, makes it possible for a company to use recordings of a person's voice to utter new things that the person never said.
The software, called Natural Voices, is not flawless -- its utterances still contain a few robotic tones and unnatural inflections -- and competitors question whether the software is a substantial step up from existing products. But some of those who have tested the technology say it is the first text-to-speech software to raise the specter of voice cloning, replicating a person's voice so perfectly that the human ear cannot tell the difference.
PHOTO: NY TIMES
"If ABC wanted to use Regis Philbin's voice for all of its automated customer-service calls, it could," said Lawrence R. Rabiner, vice president for AT&T Labs.
Potential customers for the software, which is priced in the thousands of dollars, include telephone call centers, companies that make software that reads digital files aloud, and makers of automated voice devices.
James R. Fruchterman, the chief executive of Benetech, a nonprofit organization that uses technology in social-service projects, tested the software along with a dozen people who evaluate technology for blind people, and they said they were impressed.
"Natural Voices gets into the gray area," he said, "where there is plausible deniability that it is a machine."
Rabiner said he is excited about the possibility of resurrecting renowned voices, like that of Harry Caray, the Chicago Cubs announcer who delivered rousing play-by-play broadcasts. "There are probably hours of recordings in archives," he said. Wouldn't it be great, he asked, if Harry Caray's voice could once again be broadcasting in Wrigley Field?
The technology raises several questions. Who, for example, owns the rights to a celebrity's voice? Rabiner predicted that new contracts will be drawn that include voice-licensing clauses.
With PC-generated characters already appearing in place of real ones in some movies, will computer-synthesized voices compete with those of live actors as well?
And although scientists say the technology is not yet good enough to perpetrate fraud, synthesized voices may eventually be capable of tricking people into thinking that they were getting phone calls from people they know.
To build the software that recreates unique voices -- which AT&T Labs is calling its "custom voice" product -- a person must first go to a studio where engineers record 10 hours to 40 hours of readings. Texts range from business news reports to nonsense babble. The recordings are then chopped into fragments of sounds and sorted into databases. When the software processes a text, it retrieves the sounds and re-assembles them to form new sentences.
In the case of long-dead celebrities, archival recordings could be used in the same way.
Other companies and research centers, like IBM Research and Lernout and Hauspie, are also experimenting with this technique -- which is called concatenative speech synthesis -- to improve the quality of text-to-speech software. It is a big step up, engineers say, from the speech engines that were built from whole words that had been pre-recorded. And it is also a vast improvement, some say, from the entirely computer-generated and therefore robotic sounds that are used in many versions of text-to-speech software on the market today.
Now aided by the declining cost and increasing speed of microprocessors, far smoother sentences are possible, Rabiner said. He said that the speech team at AT&T Labs, led by Juergen Schroeter, an expert in speech synthesis, had created a more refined form of the concatenative technique by breaking a person's voice into "the smallest number of units possible."
A demonstration of the technology will be available on the Web beginning Tuesday at www.naturalvoices.att.com, said Michael Dickman, a spokesman for AT&T Labs.
Still, many engineers are skeptical of claims of a completely simulated voice that is almost indistinguishable from that of a human.
"The methods and algorithms that we know of, they still need a lot more work," said P.S. Gopalakrishnan, the manager of the pervasive speech technologies group at IBM Research, which competes with AT&T Labs in the field.
Now the pressure is on to perfect the technology. Analysts at McKinsey & Co have predicted that the market for text-to-speech software will reach more than US$1 billion in the next five years. In addition to customers like call centers and manufacturers of automated voice systems, the software could also be used by publishers of video games and books-on-tape and automobile manufacturers whose cars are equipped with software that gives driving directions. In the near future, engineers have said they expect people will want high-end speech technology that enables them to interact at length with their cell phones and Palm organizers, instead of typing on and squinting at a tiny screen.
Taiwanese Olympic badminton men’s doubles gold medalist Wang Chi-lin (王齊麟) and his new partner, Chiu Hsiang-chieh (邱相榤), clinched the men’s doubles title at the Yonex Taipei Open yesterday, becoming the second Taiwanese team to win a title in the tournament. Ranked 19th in the world, the Taiwanese duo defeated Kang Min-hyuk and Ki Dong-ju of South Korea 21-18, 21-15 in a pulsating 43-minute final to clinch their first doubles title after teaming up last year. Wang, the men’s doubles gold medalist at the 2020 and 2024 Olympics, partnered with Chiu in August last year after the retirement of his teammate Lee Yang
FALSE DOCUMENTS? Actor William Liao said he was ‘voluntarily cooperating’ with police after a suspect was accused of helping to produce false medical certificates Police yesterday questioned at least six entertainers amid allegations of evasion of compulsory military service, with Lee Chuan (李銓), a member of boy band Choc7 (超克7), and actor Daniel Chen (陳大天) among those summoned. The New Taipei City District Prosecutors’ Office in January launched an investigation into a group that was allegedly helping men dodge compulsory military service using falsified medical documents. Actor Darren Wang (王大陸) has been accused of being one of the group’s clients. As the investigation expanded, investigators at New Taipei City’s Yonghe Precinct said that other entertainers commissioned the group to obtain false documents. The main suspect, a man surnamed
US Secretary of the Treasury Scott Bessent and US Trade Representative Jamieson Greer began talks with high-ranking Chinese officials in Switzerland yesterday aiming to de-escalate a dispute that threatens to cut off trade between the world’s two biggest economies and damage the global economy. The US delegation has begun meetings in Geneva with a Chinese delegation led by Chinese Vice Premier He Lifeng (何立峰), Xinhua News Agency said. Diplomats from both sides also confirmed that the talks have begun, but spoke anonymously and the exact location of the talks was not made public. Prospects for a major breakthrough appear dim, but there is
The number of births in Taiwan fell to an all-time monthly low last month, while the population declined for the 16th consecutive month, Ministry of the Interior data released on Friday showed. The number of newborns totaled 8,684, which is 704 births fewer than in March and the lowest monthly figure on record, the ministry said. That is equivalent to roughly one baby born every five minutes and an annual crude birthrate of 4.52 per 1,000 people, the ministry added. Meanwhile, 17,205 deaths were recorded, resulting in a natural population decrease of 8,521, the data showed. More people are also leaving Taiwan, with net
RSS