Enrichment is a methodology for caregivers to offer zoo animals improved psychological and physiological well-being. Although many species rely on auditory senses, sonic enrichment is rarely implemented. Zoo soundscapes are dominated by human-generated noises and do not respond meaningfully to animals' behavior. Designing interactive sonic enrichment systems for animals presents unique ergonomic, ethical, and agency-related challenges. We present a case study of such design. We deployed two novel interventions at the San Diego Zoo to allow Sampson, a music-savvy hyacinth macaw, to gain control over his sonic environment. Our results suggest that (1) the bird uses, understands, and benefits from the system, and (2) visitors play a major role in Sampson's engagement with this technology. With his new agency, the bird seemingly gains more control over his interactions with the public, creating an interspecies experience mediated by technology. The resulting animal-human-computer interaction may inform mediated interspecies experiences in the future.

Isolation is one of the largest contributors to a lack of wellbeing, increased anxiety and loneliness in older adults. In collaboration with elders in living facilities, we designed the Memory Music Box; a low-threshold platform to increase connectedness. The HCI community has contributed notable research in support of elders through monitoring, tracking and memory augmentation. Despite the Information and Communication Technologies field (ICT) advances in providing new opportunities for connection, challenges in accessibility increase the gap between elders and their loved ones. We approach this challenge by embedding a familiar form factor with innovative applications, performing design evaluations with our key target group to incorporate multi-iteration learnings. These findings culminate in a novel design that facilitates elders in crossing technology and communication barriers. Based on these findings, we discuss how future inclusive technologies for the older adults' can balance ease of use, subtlety and elements of Cognitively Sustainable Design.

Cortical recordings with high temporal resolution enable the tracking of neuronal excitation in response to stimuli. Here intra and extracranial recordings are analyzed from experiments presenting varied speech and language stimuli to human subjects. These studies demonstrate that information about speech and language is widely distributed across the brain, both spatially and temporally. Analyses using machine learning techniques can be used to track the space and time-course of performance in recognizing different words (83% on 10 spoken words), semantic categories (76% on 2 categories), etc.

The DARPA Spoken Language System (SLS) community has long taken a leadership position in designing, implementing, and globally distributing significant speech corpora widely used for advancing speech recognition research. The Wall Street Journal (WSJ) CSR Corpus described here is the newest addition to this valuable set of resources. In contrast to previous corpora, the WSJ corpus will provide DARPA its first general-purpose English, large vocabulary, natural language, high perplexity, corpus containing significant quantities of both speech data (400 hrs.) and text data (47M words), thereby providing a means to integrate speech recognition and natural language processing in application domains with high potential practical value. This paper presents the motivating goals, acoustic data design, text processing steps, lexicons, and testing paradigms incorporated into the multi-faceted WSJ CSR Corpus.

An interaction has been found between the true source language model, the training language model, and the testing language model. This interaction has implications for vocabulary independent modeling, testing methodologies, discriminative training, and the adequacy of many of the current databases for continuous speech recognition development.>

The quality of operational speech recognition performance in the presence of variable ambient noise can be significantly affected by the conditions under which patterns are initially trained, as well as by subsequent modifications of these patterns through "adaptation". These effects are clearly evidenced in a series of experiments conducted using the Dragon Systems Speech Driver in conjunction with DragonLAB (an experimenter's workstation facility), commercially available with the IBM PC Voice Communications Option and Voice Recognition Tool Kit, running on an IBM PC/AT. For each of two discrete command/control vocabularies, "Menu" (24 words) and "DOS" (29 words), training and multiple test session recordings were made at each of 55 and 65 dB ambient noise levels with an inexpensive cassette tape-recorder microphone, and at 85 dB with a close-talking noise-cancelling microphone. The seven American English-speaking subjects (4 male, 3 female) included in this database, exhibit diverse voice qualities, dialects, speech recognition familiarity, etc. A total of over 20,000 training and test utterances were collected for this database. The results of this series of experiments demonstrates the effects on recognition performance of different training stes on the same test sets, and the effects of adaptation (in a supervised learning mode), both for speaker-dependent and cross-speaker modes. For all speakers and both vocabularies, the best speaker-depentent recognition is consistently obtained when training and test materials are recorded at the same noise level. Much of the deterioration of performance across different training and test conditions can be reduced by employing supervised adaptation during the course of the recognition tests themselves, with each new test token subsequently being used as additional training to adapt its model.

Recent developments have made it possible to implement high performance speech recognition with much less computation than traditional techniques, thereby enabling real-time computation on standard microprocessors. Concepts such as time-domain acoustic-phonetic speech signal- processing as well as efficient adaptations of hidden Markov models can provide this type of capability. The Mark II system provides both speaker dependent and multiple speaker recognition of up to a 32 isolated word active vocabulary in real-time on a 2 MHz 6502, with no custom hardware, except an inexpensive microphone, pre-amp, and 8-bit A/D converter. On an initial test of 5120 test utterances (Texas Instruments isolated word data base, Spectrum, Sept., 1981), the Mark II achieved an error rate of only 0.67% (34 errors).

Measuring the performance of speech recognition systems is integral to advancing the technology as well as applying it. Appropriately designed controlled experiments are the necessary tools by which both research and commercial systems must assess the value of different algorithms and approaches. Furthermore, they form the foundation upon which potential consumers of this technology may base sound price- performance decisions for commercial applications. The objectives of this presentation are: 1) to review the major performance assessment activities presently underway, especially those of the National Bureau of Standards (U.S. Dept. of Commerce) and the NATO Research Study Group on Speech Recognition, 2) to present a set of recommendations and evaluation guidelines recently compiled from speech researchers based in academia, industry, and government, 3) to reference a number of specific evaluation proposals generated within the speech community, and 4) to summarize and briefly describe a compilation of speech data bases which under certain conditions have been or may become available.

The HEAR acoustic processor combines standard frequency-domain and cycle-synchronous time-domain parameters. Output segments, usually 10 msec. in length, vary dynamically from .1 msec. to over 100 msec. to capture significant events in the underlying acoustic phone structure. Segment labels are determined by matching against a set of about 200 automatically selected prototypes. Some statistics on the fraction of segments correctly labeled (from a choice of 52 labels) and their most likely confusions are included. Speech recognition results obtained using the HEAR acoustic processor in conjunction with the training and decoding procedures of the IBM Research Continuous Speech Recognition mainline system are presented. On a set of 125 test sentences (1010 words) of the "New Raleigh Language" (artificial language, 250 word vocabulary, perplexity 7.27), the sentence recognition rate is 100%. On a set of 10 test sentences (282 words) of the "Laser-1000 Language" (natural language, 1000 word vocabulary, perplexity 21.1), the word recognition rate is 80%. Although it generally is difficult to ascribe errors to specific system components, three classes of errors are observed: 1) the correct word is not hypothesized; therefore acoustic match is not performed, 10.3% words, 2) the correct word is hypothesized but search is pruned prior to the construction of longer phrases including it, 6.4%, 3) the correct word is hypothesized, fully matched, and rejected in favor of an incorrect word, 3.2%. Errors of the third class are comprised exclusively of short function words (e.g. "the", "of", etc.), 2.2%, and deleted commas (realized acoustically by optional interword pauses), 1.0%.