The in-car PC boom that was predicted to be in full swing by now hasn't happened, and it may be delayed another year to 18 months as automakers and vendors run up against challenges in implementing speech recognition systems, according to a report by Charles J. Murray in the online EE Times. The delay is a big disappointment for manufacturers that have invested millions in the development and promotion of in-vehicle computers. But because speech recognition systems are critical to addressing potential driver distraction issues (which are serious enough to warranty on ongoing investigation by the National Highway Traffic Safety Administration), carmakers want them to be as close to perfect as possible. And they're not there yet, according to industry observers. Those problems are a key reason why Cadillac has delayed the introduction of its Infotainment system from fall of this year until late 2001, and why Visteon Corp. has yet to put its ICES (information, communication, safety, and security) technology into a production vehicle, according to software makers and industry analysts. Industry analysts also blame the lack of a good speech system for the disappointing performance of Clarion's AutoPC. Clarion Technologies Inc. had expected to be selling the system at a rate of thousands per month by 2000, but has sold just 3,500 units in two and a half years. Eyes On the Road, Hands On the Wheel The rush to create more effective speech systems is seen as critical for automakers. Several of them, most notably Ford and General Motors, have espoused an "eyes-on-the-road, hands-on-the-wheel" philosophy as they work to incorporate new electronic capabilities into automobiles. That philosophy is seen as especially important now, in light of the recent passage of state laws restricting drivers' use of cell phones, along with the NHTSA investigation. But automakers said they can't bring eyes-on-the-road, hands-on-the-wheel techniques to vehicles unless they have good speech recognition systems. That's why GM has forged partnerships with General Magic Inc. and Nuance Communications Inc. to work on systems. It's also why Ford has allied itself with speech recognition developer Lernout & Hauspie Speech Products, which filed for Chapter 11 protection last week following management missteps. Automakers said they plan to continue to work on speech recognition systems, but they deny there are problems. Indeed, OnStar representatives said the company's Virtual Advisor, an off-board speech-based service that provides e-mail, news, and stock quotes, is coming out as scheduled at the end of this year. Delivery of the system has already begun in the Northeast, and industry analysts said they are impressed by it. But in-car PCs, which use onboard electronics, have not fared as well. Cadillac's much-ballyhooed Infotainment system, which was already supposed to be available on the Cadillac Deville, is at least a year behind schedule, according to Murray's report. A GM spokesman declined to comment on reasons for the delay, except to say that there are "technical issues." Similarly, a Visteon spokeswoman said the ICES system is in development programs with several OEMs, but would not say when it will reach production. At the 1998 Society of Automotive Engineers conference in Detroit, however, Visteon and Ford predicted the first units would be in vehicles by 2000. Automotive engineers and software makers do acknowledge that equipping car systems for speech recognition has proved a more formidable task than had been expected. Noisy Confusion The heart of the problem is that vehicles, unlike desktop PCs, are subjected to a wide variety of noises that can confuse software-based speech recognizers. Compounding the problem is that in-car speech recognition is often done by remote servers over cellular links. If speech recognition is done over a cellular link, the system also must deal with such issues as line echo, electrical interference, and poor signal strength. Automotive engineers say the problems aren't insurmountable. Software makers say the problems are magnified at higher vehicle speeds. Most voice recognition systems currently claim accuracies of 90 to 95 percent, but some said such claims are averages, which hold true at 30 mph but not at higher speeds. At 70 mph, for example, the accuracy figure dips to about 70 percent, according to some engineers. If occupants crack open a window, turn on the radio, or blast the air conditioner, the accuracy figures drop even more. Some engineers disagree with the 70 percent accuracy figure, even for high-speed applications. Automotive engineers have found ways to deal with high speeds, they claim. Some engineers also say unexpected noises, such as children in the back seat, opening and closing windows, and general cracks and pops are of greater concern than high speed. Automakers are concerned about even the smallest lack of accuracy because it could place greater load on the driver, who ideally should be free to concentrate on traffic and driving conditions. Stories of drivers struggling with voice recognition systems are already commonplace, even though the technology has been available for only a short time. Such stories are a concern among industry analysts as well as automakers. Some believe the dilemmas facing automotive speech recognition may be a result of hardware rather than software. If that's the case, the problem would be more focused on in-car PCs, such as the Infotainment system or ICES, according to analysts. Systems such as OnStar's Virtual Advisor use off-board, server-based processing. There are strategies to deal with voice recognition in a car with multiple passengers, according to Murray's story. For example, audio systems can be set up to "listen" preferentially to the person behind the steering wheel and treat other voices as "noise" to be canceled. But it is not yet clear how successful such strategies are. Some software makers, such as Clarity and Conversay, believe the solution lies in the use of specialized software and better microphones. Clarity, for example, offers a technology known as Clear Voice Capture, which extracts the voice signal of interest. The company said the technology provides an improvement over noise suppression systems, which have difficulty with signals that have components overlapping with voice signals. Similarly, Conversay offers filtration techniques that separate speech signals from noise signals and narrowly focus on the speaker. The system employs two microphones -- one on the passenger side and another on the driver side -- and is focused more on distributed speech, for which processing power is split between the client and server. Engineers are also reportedly looking at microphone technology as a way to boost accuracy. But the best, the so-called array microphones, cost between $100 and $180, and that's beyond the acceptable limit for automotive applications. Many in the industry are unconvinced by automakers' claims. Many analysts say it is still unclear exactly when speech recognition technology will be ready for the mass market.
0 Comments