As computational power and speech recognition algorithms improve, the consumer market will see better-performing speech recognition applications. The cell phone and Internet-related service industry have further enhanced speech recognition applications using artificial intelligence and statistical data-mining techniques. These improvements to speech recognition technology (SRT) may one day help astronauts on future deep space human missions that require control of complex spacecraft systems or

more »

... pacesuit applications by voice. Though SRT and more advanced speech recognition techniques show promise, use of this technology for a space application such as vehicle/habitat/spacesuit requires careful considerations. This paper provides considerations and guidance for the use of SRT in voice-controlled spacecraft systems (VCSS) applications for space missions, specifically in command-and-control (C2) applications where the commanding is user-initiated. First, current SRT limitations as known at the time of this report are given. Then, highlights of SRT used in the space program provide the reader with a history of some of the human spaceflight applications and research. Next, an overview of the speech production process and the intrinsic variations of speech are provided. Finally, general guidance and considerations are given for the development of a VCSS using a human-centered design approach for space applications that includes vocabulary selection and performance testing, as well as VCSS considerations for C2 dialogue management design, feedback, error handling, and evaluation/usability testing. Keywords-command and control, human-centered design, recognition errors, speech recognition technology I. INTRODUCTION Since the first commercial use of speech recognition technology (SRT) in the 1980s-primarily in the telephone industry-SRT has improved concerning speaker recognition performance and dialogue design. Today, many commercial industries, including banking, airline reservations, medical, automotive, and legal (to name a few) use SRT. The iPhone industry has advanced human-computer interface (HCI) dialogue development using artificial intelligence (AI) and natural language processing (NLP). It will soon become people's chief means of interacting with computing devices and systems. For future space missions, these advancements may one day help astronauts control complex spacecraft systems, information storage, and retrieval, or spacesuit controls by voice [6] . Currently, more than 50 people in the Mission Control Center (MCC) support the operation of the Space Station. They serve as an extra pair of eyes to the astronaut overseeing the numerous station systems and handling emergencies. As humanity advances farther from Earth, the round-trip communication delays between Earth and the spacecraft increases, requiring more onboard MCC functionality to maintain and control the vehicle. Hence, deep space missions to Mars and beyond will place challenging constraints on the crew that will demand an efficient and effective HCI to control a highly complex vehicle/habitat system. NASA Human Research Program (HRP) has identified inadequate HCI as a risk for future missions. New tools and procedures to aid the crew in operating a complex spacecraft will be required. Voice-controlled spacecraft systems (VCSS) could potentially help solve the HCI risk. Though SRT has come a long way, it still struggles with challenges such as background noise and human speech variability influenced by task loading and the user's psychological and physiological health. SRT recognizes the words spoken but lacks an understanding of the meaning of the words. The responsibility for interpreting the users meaning lies with the VCSS application dialogue between the user and the machine. However, the machine-understanding dialogue is still a long way from understanding the speaker's intended meaning. Incorrectly recognized words are treated cautiously as the system could branch into a wrong part of the application software code--furthering the likelihood of more recognition errors. Implemented correctly, VCSS in a data entry application permits increased machine or system operator efficiency with a high level of recovering from recognition errors (RE). If incorrectly developed, the task workload can increase, resulting in potentially more REs, making the system unacceptable to the user.