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.

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.

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.

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.

Brain activity evidence for recognition without recollection after early hippocampal damage

Amnesic patients with early and seemingly isolated hippocampal injury show relatively normal recognition memory scores. The cognitive profile of these patients raises the possibility that this recognition performance is maintained mainly by stimulus familiarity in the absence of recollection of contextual information. Here we report electrophysiological data on the status of recognition memory in one of the patients, Jon. Jon's recognition of studied words lacks the event-related potential (ERP) index of recollection, viz., an increase in the late positive component (500–700 ms), under conditions that elicit it reliably in normal subjects. On the other hand, a decrease of the ERP amplitude between 300 and 500 ms, also reliably found in normal subjects, is well preserved. This so-called N400 effect has been linked to stimulus familiarity in previous ERP studies of recognition memory. In Jon, this link is supported by the finding that his recognized and unrecognized studied words evoked topographically distinct ERP effects in the N400 time window. These data suggest that recollection is more dependent on the hippocampal formation than is familiarity, consistent with the view that the hippocampal formation plays a special role in episodic memory, for which recollection is so critical.

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.

Computer speech synthesis: its status and prospects.

Computer speech synthesis has reached a high level of performance, with increasingly sophisticated models of linguistic structure, low error rates in text analysis, and high intelligibility in synthesis from phonemic input. Mass market applications are beginning to appear. However, the results are still not good enough for the ubiquitous application that such technology will eventually have. A number of alternative directions of current research aim at the ultimate goal of fully natural synthetic speech. One especially promising trend is the systematic optimization of large synthesis systems with respect to formal criteria of evaluation. Speech recognition has progressed rapidly in the past decade through such approaches, and it seems likely that their application in synthesis will produce similar improvements.

Integration of speech with natural language understanding.

The integration of speech recognition with natural language understanding raises issues of how to adapt natural language processing to the characteristics of spoken language; how to cope with errorful recognition output, including the use of natural language information to reduce recognition errors; and how to use information from the speech signal, beyond just the sequence of words, as an aid to understanding. This paper reviews current research addressing these questions in the Spoken Language Program sponsored by the Advanced Research Projects Agency (ARPA). I begin by reviewing some of the ways that spontaneous spoken language differs from standard written language and discuss methods of coping with the difficulties of spontaneous speech. I then look at how systems cope with errors in speech recognition and at attempts to use natural language information to reduce recognition errors. Finally, I discuss how prosodic information in the speech signal might be used to improve understanding.

Commercial applications of speech interface technology: an industry at the threshold.

Speech interface technology, which includes automatic speech recognition, synthetic speech, and natural language processing, is beginning to have a significant impact on business and personal computer use. Today, powerful and inexpensive microprocessors and improved algorithms are driving commercial applications in computer command, consumer, data entry, speech-to-text, telephone, and voice verification. Robust speaker-independent recognition systems for command and navigation in personal computers are now available; telephone-based transaction and database inquiry systems using both speech synthesis and recognition are coming into use. Large-vocabulary speech interface systems for document creation and read-aloud proofing are expanding beyond niche markets. Today's applications represent a small preview of a rich future for speech interface technology that will eventually replace keyboards with microphones and loud-speakers to give easy accessibility to increasingly intelligent machines.

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.

Speech technology in 2001: new research directions.

Research in speech recognition and synthesis over the past several decades has brought speech technology to a point where it is being used in "real-world" applications. However, despite the progress, the perception remains that the current technology is not flexible enough to allow easy voice communication with machines. The focus of speech research is now on producing systems that are accurate and robust but that do not impose unnecessary constraints on the user. This chapter takes a critical look at the shortcomings of the current speech recognition and synthesis algorithms, discusses the technical challenges facing research, and examines the new directions that research in speech recognition and synthesis must take in order to form the basis of new solutions suitable for supporting a wide range of applications.

Reactivation of encoding-related brain activity during memory retrieval

Neuronal models predict that retrieval of specific event information reactivates brain regions that were active during encoding of this information. Consistent with this prediction, this positron-emission tomography study showed that remembering that visual words had been paired with sounds at encoding activated some of the auditory brain regions that were engaged during encoding. After word-sound encoding, activation of auditory brain regions was also observed during visual word recognition when there was no demand to retrieve auditory information. Collectively, these observations suggest that information about the auditory components of multisensory event information is stored in auditory responsive cortex and reactivated at retrieval, in keeping with classical ideas about “redintegration,” that is, the power of part of an encoded stimulus complex to evoke the whole experience.

Temporal events in cyclopean vision.

The majority of neurons in the primary visual cortex of primates can be activated by stimulation of either eye; moreover, the monocular receptive fields of such neurons are located in about the same region of visual space. These well-known facts imply that binocular convergence in visual cortex can explain our cyclopean view of the world. To test the adequacy of this assumption, we examined how human subjects integrate binocular events in time. Light flashes presented synchronously to both eyes were compared to flashes presented alternately (asynchronously) to one eye and then the other. Subjects perceived very-low-frequency (2 Hz) asynchronous trains as equivalent to synchronous trains flashed at twice the frequency (the prediction based on binocular convergence). However, at higher frequencies of presentation (4-32 Hz), subjects perceived asynchronous and synchronous trains to be increasingly similar. Indeed, at the flicker-fusion frequency (approximately 50 Hz), the apparent difference between the two conditions was only 2%. We suggest that the explanation of these anomalous findings is that we parse visual input into sequential episodes.

Scientific bases of human-machine communication by voice.

The scientific bases for human-machine communication by voice are in the fields of psychology, linguistics, acoustics, signal processing, computer science, and integrated circuit technology. The purpose of this paper is to highlight the basic scientific and technological issues in human-machine communication by voice and to point out areas of future research opportunity. The discussion is organized around the following major issues in implementing human-machine voice communication systems: (i) hardware/software implementation of the system, (ii) speech synthesis for voice output, (iii) speech recognition and understanding for voice input, and (iv) usability factors related to how humans interact with machines.

The role of voice input for human-machine communication.

Optimism is growing that the near future will witness rapid growth in human-computer interaction using voice. System prototypes have recently been built that demonstrate speaker-independent real-time speech recognition, and understanding of naturally spoken utterances with vocabularies of 1000 to 2000 words, and larger. Already, computer manufacturers are building speech recognition subsystems into their new product lines. However, before this technology can be broadly useful, a substantial knowledge base is needed about human spoken language and performance during computer-based spoken interaction. This paper reviews application areas in which spoken interaction can play a significant role, assesses potential benefits of spoken interaction with machines, and compares voice with other modalities of human-computer interaction. It also discusses information that will be needed to build a firm empirical foundation for the design of future spoken and multimodal interfaces. Finally, it argues for a more systematic and scientific approach to investigating spoken input and performance with future language technology.