The benefit of smart virtual assistants and their acceptance by the users depend on how well they recognize spoken commands and respond to them in real-life environments – and the basis for good performance are automatic speech recognizers. VoCAS (Voice Control Analysis System) from HEAD acoustics reveals speech recognizer performance with unprecedented ease and accuracy, and is used to benchmark different speech recognition systems.
The ultimate example of the German company's ability to address objective signal evaluation in complex scenarios, the VoCAS software objectively tests and evaluates speech recognition performance in smart home applications, vehicles, or smartphones - to name just a few - emulating a realistic environment for each respective application. It is part of HEAD acoustics' sophisticated measuring and playback framework that mimics real-life situations as closely as possible, incorporating critical factors in measuring speech recognizer quality with a unique, comprehensive approach. VoCAS considers the acoustic environment, background noise, different talkers, different languages, and even accents - all factors that remained until know uncorrelated.
Because attention to detail means attention to variation, this true-to-life diligence also involves using HEAD acoustics' HMS artificial heads, equipped with an artificial mouth using specially developed loudspeakers simulating the human mouth sound field. And VoCAS allows the precise individual calibration of each artificial mouth. This approach allows mimicking the natural voice transmission path, which is the only way to ensure a realistic human voice sound field generation.
With VoCAS' customizable and reproducible test sequences adapted to the respective application, users gain essential information to optimize and validate the speech recognition performance, with up to four simultaneous talker positions – even in noisy, reverberant environments.
The HMS artificial heads are integrated with HEAD acoustics hardware platform labCORE, allowing VoCAS to run complex test scenarios with up to four talkers simultaneously, automated and calibrated speech recordings, and a simulation of different room environments and noise conditions. This makes VoCAS ideally suited for benchmarking various acoustical device interfaces in conjunction with speech recognition systems. Of course, VoCAS also allows users to import existing speech material and cut, filter, and adjust audio files to defined speech levels.
With the continuous feature expansion and updates, VoCAS also makes it easy for users to realize the full potential of the software and its ecosystem. For example, its extensive test automation now includes user-programmable test sequences, fully automatic equalization, automated evaluation, and the statistical analysis of detection and error rates. VoCAS also combines a database application that integrates into a comprehensive setup for the synchronized and calibrated playback of speech and spatially recorded data.
Introduced in 2016 by HEAD acoustics, and since then continuously improved, VoCAS is now able to test and evaluate any speech recognition system systematically and under realistic, reproducible conditions. The fact that it enables automated, complex, and realistic test scenarios with up to four talkers, background noise, and reverberation and echo, make it ideally suited for optimizing and benchmarking devices employing or connected to speech recognition systems.
HEAD acoustics GmbH is one of the world's leading companies offering holistic solutions for sound and vibration analysis, enjoying global recognition in the telecom market due to its pioneering role in the development of hardware and software for the measurement, analysis and optimization of voice and audio quality as well as customer-specific solutions and services.
HEAD acoustics' range of services covers sound engineering for technical products, investigation of environmental noise, speech quality engineering as well as consulting, training and support. The company is headquartered in Herzogenrath, near Aachen, in Germany, and has subsidiaries in China, France, Italy, Japan, South Korea, the UK and the USA as well as numerous sales partners worldwide.
www.head-acoustics.com
