Developments and Directions in Speech Recognition and Understanding , Part 1 T

T o advance research, it is important to identify promising future research directions , especially those that have not been adequately pursued or funded in the past. The working group producing this article was charged to elicit from the human language technology (HLT) community a set of well-considered directions or rich areas for future research that could lead to major paradigm shifts in the field of automatic speech recognition (ASR) and understanding. ASR has been an area of great interest and activity to the signal processing and HLT communities over the past several decades. As a first step, this group reviewed major developments in the field and the circumstances that led to their success and then focused on areas it deemed especially fertile for future research. Part 1 of this article will focus on historically significant developments in the ASR area, including several major research efforts that were guided by different funding agencies, and suggest general areas in which to focus research. Part 2 (to appear in the next issue) will explore in more detail several new avenues holding promise for substantial improvements in ASR performance. These entail cross-disciplinary research and specific approaches to address three-to-five-year grand challenges aimed at stimulating advanced research by dealing with realistic tasks of broad interest. SIGNIFICANT DEVELOPMENTS IN SPEECH RECOGNITION AND UNDERSTANDING The period since the mid-1970s has witnessed the multidisciplinary field of ASR proceed from its infancy to its coming of age and into a quickly growing number of practical applications and commercial markets. Despite its many achievements, however, ASR still remains far from being a solved problem. As in the past, we expect that further research and development will enable us to create increasingly powerful systems, deploy-able on a worldwide basis. This section briefly reviews highlights of major developments in ASR in five areas: infrastructure, knowledge representation, models and algorithms, search, and metadata. Broader and deeper discussions of these areas can INFRASTRUCTURE Moore's Law observes long-term progress in computer development and predicts doubling the amount of computation achievable for a given cost every 12 to 18 months, as well as a comparably shrinking cost of memory. These developments have been instrumental in enabling ASR researchers to run increasingly complex algorithms in sufficiently short time frames (e.g., meaningful experiments that can be done in less than a day) to make great progress since 1975. The availability of common speech corpora for speech training, …