State of the art in continuous speech recognition.

In the past decade, tremendous advances in the state of the art of automatic speech recognition by machine have taken place. A reduction in the word error rate by more than a factor of 5 and an increase in recognition speeds by several orders of magnitude (brought about by a combination of faster recognition search algorithms and more powerful computers), have combined to make high-accuracy, speaker-independent, continuous speech recognition for large vocabularies possible in real time, on off-the-shelf workstations, without the aid of special hardware. These advances promise to make speech recognition technology readily available to the general public. This paper focuses on the speech recognition advances made through better speech modeling techniques, chiefly through more accurate mathematical modeling of speech sounds.

Toward the ultimate synthesis/recognition system.

This paper predicts speech synthesis, speech recognition, and speaker recognition technology for the year 2001, and it describes the most important research problems to be solved in order to arrive at these ultimate synthesis and recognition systems. The problems for speech synthesis include natural and intelligible voice production, prosody control based on meaning, capability of controlling synthesized voice quality and choosing individual speaking style, multilingual and multidialectal synthesis, choice of application-oriented speaking styles, capability of adding emotion, and synthesis from concepts. The problems for speech recognition include robust recognition against speech variations, adaptation/normalization to variations due to environmental conditions and speakers, automatic knowledge acquisition for acoustic and linguistic modeling, spontaneous speech recognition, naturalness and ease of human-machine interaction, and recognition of emotion. The problems for speaker recognition are similar to those for speech recognition. The research topics related to all these techniques include the use of articulatory and perceptual constraints and evaluation methods for measuring the quality of technology and systems.

Voice-processing technologies--their application in telecommunications.

As the telecommunications industry evolves over the next decade to provide the products and services that people will desire, several key technologies will become commonplace. Two of these, automatic speech recognition and text-to-speech synthesis, will provide users with more freedom on when, where, and how they access information. While these technologies are currently in their infancy, their capabilities are rapidly increasing and their deployment in today's telephone network is expanding. The economic impact of just one application, the automation of operator services, is well over $100 million per year. Yet there still are many technical challenges that must be resolved before these technologies can be deployed ubiquitously in products and services throughout the worldwide telephone network. These challenges include: (i) High level of accuracy. The technology must be perceived by the user as highly accurate, robust, and reliable. (ii) Easy to use. Speech is only one of several possible input/output modalities for conveying information between a human and a machine, much like a computer terminal or Touch-Tone pad on a telephone. It is not the final product. Therefore, speech technologies must be hidden from the user. That is, the burden of using the technology must be on the technology itself. (iii) Quick prototyping and development of new products and services. The technology must support the creation of new products and services based on speech in an efficient and timely fashion. In this paper I present a vision of the voice-processing industry with a focus on the areas with the broadest base of user penetration: speech recognition, text-to-speech synthesis, natural language processing, and speaker recognition technologies. The current and future applications of these technologies in the telecommunications industry will be examined in terms of their strengths, limitations, and the degree to which user needs have been or have yet to be met. Although noteworthy gains have been made in areas with potentially small user bases and in the more mature speech-coding technologies, these subjects are outside the scope of this paper.

Effects of muscarinic blockade in perirhinal cortex during visual recognition

Stimulus recognition in monkeys is severely impaired by destruction or dysfunction of the perirhinal cortex and also by systemic administration of the cholinergic-muscarinic receptor blocker, scopolamine. These two effects are shown here to be linked: Stimulus recognition was found to be significantly impaired after bilateral microinjection of scopolamine directly into the perirhinal cortex, but not after equivalent injections into the laterally adjacent visual area TE or into the dentate gyrus of the overlying hippocampal formation. The results suggest that the formation of stimulus memories depends critically on cholinergic-muscarinic activation of the perirhinal area, providing a new clue to how stimulus representations are stored.

Image recognition: Visual grouping, recognition, and learning

Vision extracts useful information from images. Reconstructing the three-dimensional structure of our environment and recognizing the objects that populate it are among the most important functions of our visual system. Computer vision researchers study the computational principles of vision and aim at designing algorithms that reproduce these functions. Vision is difficult: the same scene may give rise to very different images depending on illumination and viewpoint. Typically, an astronomical number of hypotheses exist that in principle have to be analyzed to infer a correct scene description. Moreover, image information might be extracted at different levels of spatial and logical resolution dependent on the image processing task. Knowledge of the world allows the visual system to limit the amount of ambiguity and to greatly simplify visual computations. We discuss how simple properties of the world are captured by the Gestalt rules of grouping, how the visual system may learn and organize models of objects for recognition, and how one may control the complexity of the description that the visual system computes.

Training and search methods for speech recognition.

Speech recognition involves three processes: extraction of acoustic indices from the speech signal, estimation of the probability that the observed index string was caused by a hypothesized utterance segment, and determination of the recognized utterance via a search among hypothesized alternatives. This paper is not concerned with the first process. Estimation of the probability of an index string involves a model of index production by any given utterance segment (e.g., a word). Hidden Markov models (HMMs) are used for this purpose [Makhoul, J. & Schwartz, R. (1995) Proc. Natl. Acad. Sci. USA 92, 9956-9963]. Their parameters are state transition probabilities and output probability distributions associated with the transitions. The Baum algorithm that obtains the values of these parameters from speech data via their successive reestimation will be described in this paper. The recognizer wishes to find the most probable utterance that could have caused the observed acoustic index string. That probability is the product of two factors: the probability that the utterance will produce the string and the probability that the speaker will wish to produce the utterance (the language model probability). Even if the vocabulary size is moderate, it is impossible to search for the utterance exhaustively. One practical algorithm is described [Viterbi, A. J. (1967) IEEE Trans. Inf. Theory IT-13, 260-267] that, given the index string, has a high likelihood of finding the most probable utterance.

Positron-emission tomography imaging of long-term shape recognition challenges

Long-term visual memory performance was impaired by two types of challenges: a diazepam challenge on acquisition and a sensory challenge on recognition. Using positron-emission tomography regional cerebral blood flow imaging, we studied the effect of these challenges on regional brain activation during the delayed recognition of abstract visual shapes as compared with a baseline fixation task. Both challenges induced a significant decrease in differential activation in the left fusiform gyrus, suggesting that this region is involved in the automatic or volitional comparison of incoming and stored stimuli. In contrast, thalamic differential activation increased in response to memory challenges. This increase might reflect enhanced retrieval attempts as a compensatory mechanism for restoring recognition performance.

Visual constraints in foraging bumblebees: Flower size and color affect search time and flight behavior

In optimal foraging theory, search time is a key variable defining the value of a prey type. But the sensory-perceptual processes that constrain the search for food have rarely been considered. Here we evaluate the flight behavior of bumblebees (Bombus terrestris) searching for artificial flowers of various sizes and colors. When flowers were large, search times correlated well with the color contrast of the targets with their green foliage-type background, as predicted by a model of color opponent coding using inputs from the bees' UV, blue, and green receptors. Targets that made poor color contrast with their backdrop, such as white, UV-reflecting ones, or red flowers, took longest to detect, even though brightness contrast with the background was pronounced. When searching for small targets, bees changed their strategy in several ways. They flew significantly slower and closer to the ground, so increasing the minimum detectable area subtended by an object on the ground. In addition, they used a different neuronal channel for flower detection. Instead of color contrast, they used only the green receptor signal for detection. We relate these findings to temporal and spatial limitations of different neuronal channels involved in stimulus detection and recognition. Thus, foraging speed may not be limited only by factors such as prey density, flight energetics, and scramble competition. Our results show that understanding the behavioral ecology of foraging can substantially gain from knowledge about mechanisms of visual information processing.

Visual habit formation in monkeys with neurotoxic lesions of the ventrocaudal neostriatum

Visual habit formation in monkeys, assessed by concurrent visual discrimination learning with 24-h intertrial intervals (ITI), was found earlier to be impaired by removal of the inferior temporal visual area (TE) but not by removal of either the medial temporal lobe or inferior prefrontal convexity, two of TE's major projection targets. To assess the role in this form of learning of another pair of structures to which TE projects, namely the rostral portion of the tail of the caudate nucleus and the overlying ventrocaudal putamen, we injected a neurotoxin into this neostriatal region of several monkeys and tested them on the 24-h ITI task as well as on a test of visual recognition memory. Compared with unoperated monkeys, the experimental animals were unaffected on the recognition test but showed an impairment on the 24-h ITI task that was highly correlated with the extent of their neostriatal damage. The findings suggest that TE and its projection areas in the ventrocaudal neostriatum form part of a circuit that selectively mediates visual habit formation.

The neural development and organization of letter recognition: Evidence from functional neuroimaging, computational modeling, and behavioral studies

Although much of the brain’s functional organization is genetically predetermined, it appears that some noninnate functions can come to depend on dedicated and segregated neural tissue. In this paper, we describe a series of experiments that have investigated the neural development and organization of one such noninnate function: letter recognition. Functional neuroimaging demonstrates that letter and digit recognition depend on different neural substrates in some literate adults. How could the processing of two stimulus categories that are distinguished solely by cultural conventions become segregated in the brain? One possibility is that correlation-based learning in the brain leads to a spatial organization in cortex that reflects the temporal and spatial clustering of letters with letters in the environment. Simulations confirm that environmental co-occurrence does indeed lead to spatial localization in a neural network that uses correlation-based learning. Furthermore, behavioral studies confirm one critical prediction of this co-occurrence hypothesis, namely, that subjects exposed to a visual environment in which letters and digits occur together rather than separately (postal workers who process letters and digits together in Canadian postal codes) do indeed show less behavioral evidence for segregated letter and digit processing.

Lightness constancy in primary visual cortex

When the illumination of a visual scene changes, the quantity of light reflected from objects is altered. Despite this, the perceived lightness of the objects generally remains constant. This perceptual lightness constancy is thought to be important behaviorally for object recognition. Here we show that interactions from outside the classical receptive fields of neurons in primary visual cortex modulate neural responses in a way that makes them immune to changes in illumination, as is perception. This finding is consistent with the hypothesis that the responses of neurons in primary visual cortex carry information about surface lightness in addition to information about form. It also suggests that lightness constancy, which is sometimes thought to involve “higher-level” processes, is manifest at the first stage of visual cortical processing.

Speech recognition technology: a critique.

This paper introduces the session on advanced speech recognition technology. The two papers comprising this session argue that current technology yields a performance that is only an order of magnitude in error rate away from human performance and that incremental improvements will bring us to that desired level. I argue that, to the contrary, present performance is far removed from human performance and a revolution in our thinking is required to achieve the goal. It is further asserted that to bring about the revolution more effort should be expended on basic research and less on trying to prematurely commercialize a deficient technology.

Processing of speech signals for physical and sensory disabilities.

Assistive technology involving voice communication is used primarily by people who are deaf, hard of hearing, or who have speech and/or language disabilities. It is also used to a lesser extent by people with visual or motor disabilities. A very wide range of devices has been developed for people with hearing loss. These devices can be categorized not only by the modality of stimulation [i.e., auditory, visual, tactile, or direct electrical stimulation of the auditory nerve (auditory-neural)] but also in terms of the degree of speech processing that is used. At least four such categories can be distinguished: assistive devices (a) that are not designed specifically for speech, (b) that take the average characteristics of speech into account, (c) that process articulatory or phonetic characteristics of speech, and (d) that embody some degree of automatic speech recognition. Assistive devices for people with speech and/or language disabilities typically involve some form of speech synthesis or symbol generation for severe forms of language disability. Speech synthesis is also used in text-to-speech systems for sightless persons. Other applications of assistive technology involving voice communication include voice control of wheelchairs and other devices for people with mobility disabilities.