PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Speech Recognition Software”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 163 records · Page 9Linked to original sources
PubMed1998

Computer-based speech recognition as a replacement for medical transcription.

OBJECTIVE: We have implemented computerized speech recognition in a high-volume clinical setting using a newly developed commercial software system. This paper compares the performance of the computerized system with conventional transcription during a trial week followed by 3 months of routine clinical use. CONCLUSION: The speech recognition system was used for 97% of the cases during the trial week and 87% of cases during the months of continuous use. For a similar mixture of cases, no change occurred in the length of reports after introduction of the computerized system. Speech recognition decreased the time until the report became available by 99% and resulted in a substantial savings in transcription costs. We conclude that speech recognition by computer is practical in a high-volume clinical implementation.

Cost-Benefit Analysis↗
PubMed1985

Voice recognition device as a computer interface for motor and speech impaired people.

A voice recognition device has been identified as an interface for personal computer control by patients presenting with high-level spinal cord injuries and mild dysarthria. The device enables a person to bypass the traditional keyboard and activate a computer through voice control. The user simply creates templates of a spoken vocabulary in computer memory. The computer then matches real-time spoken words to stored templates for activation. The system has been clinically tested with one 10-year-old boy who has C1-C2 quadriplegia and a 19-year-old man who sustained a C6 spinal cord injury and dysarthria secondary to head injury. Each patient created a vocabulary for computer storage to run educational software packages and games. Accuracy rates for computer speech recognition were measured in multiple practice sessions. Intelligibility of single words produced by the dysarthric speaker was measured also. Both patients activated computer programs through voice control. Recognition rates ranged from 45 to 60% for the first patient, and 79 to 96% for the second patient. A mean success rate for voice recognition across trials with both patients was approximately 80%. The device increased the dysarthric speaker's articulatory precision. Results indicate that the system might be appropriate for rehabilitation programs though further technologic refinement of the device would increase its effectiveness.

Adult↗
PubMed1997

Remediating production of tense morphology improves verb retrieval in chronic aphasia.

Production of tense markers in C-VIC, a computerized visual communication system, was utilized as a treatment for three patients with severe expressive aphasia. Patients practiced constructing C-VIC tense marked sentences and then producing English equivalents. After training, all patients demonstrated significant improvements in English verb retrieval and production of correct tense morphology. Generalization of morphological rules for past tense production was seen for regular, but not irregular verbs. These results support the LaPointe and Dell (1989) extension of the Garrett (1975, 1992) model specifying a search through so-called verb phrase notion stores as a process mediating transition from functional to positional levels, but also suggest an additional constraint on the output of the verb notion store search.

Adult↗
PubMed1997

Potential problems associated with use of speech recognition products.

Commercial speech recognition products are being used increasingly as alternate input devices for computers, particularly by persons with physical disabilities. These discrete speech dictation systems require the user to insert brief but distinct pauses after each spoken word. Anecdotal evidence suggests that some persons using these products experience moderate to severe problems with their voices, such as hoarseness, sore throats, and even complete loss of voice. This preliminary study, which includes data gathered from survey dissemination and clinical studies, indicates that persons with cumulative trauma disorder may be the most susceptible to these voice problems. Also, we hypothesized that in using these discrete speech recognition systems, there may be a tendency to maintain constant pitch, volume, and inflection, keeping the vocal tract musculature in a fixed position. Maintaining this fixed position for extended periods may result in muscle fatigue and, eventually, injury to the laryngeal musculature. Further studies are needed, however, to investigate the effects suggested here. In the meantime, we recommend that users become informed about the unnatural speech patterns used with discrete speech recognition systems; learn to use good vocal hygiene, such as performing warm-up and cool-down voice exercises; and use alternate methods of input along with the speech recognition product.

Aphonia↗
PubMed2006

Are fMRI event-related response constant in time? A model selection answer.

An accurate estimation of the hemodynamic response function (HRF) in functional magnetic resonance imaging (fMRI) is crucial for a precise spatial and temporal estimate of the underlying neuronal processes. Recent works have proposed non-parametric estimation of the HRF under the hypotheses of linearity and stationarity in time. Biological literature suggests, however, that response magnitude may vary with attention or ongoing activity. We therefore test a more flexible model that allows for the variation of the magnitude of the HRF with time in a maximum likelihood framework. Under this model, the magnitude of the HRF evoked by a single event may vary across occurrences of the same type of event. This model is tested against a simpler model with a fixed magnitude using information theory. We develop a standard EM algorithm to identify the event magnitudes and the HRF. We test this hypothesis on a series of 32 regions (4 ROIS on eight subjects) of interest and find that the more flexible model is better than the usual model in most cases. The important implications for the analysis of fMRI time series for event-related neuroimaging experiments are discussed.

Algorithms↗
PubMed1989

Microcomputer voice-recognition program in a hospital emergency department.

A software program for voice-controlled text creation was used on a microcomputer in the emergency medical department of a large hospital. It was found that automated speech recognition (ASR) permitted doctors to produce their reports faster and more accurately than handwriting or dictation to tape. In addition, ASR reporting is cheaper than dictation to tape. Other advantages include the automatic creation of computer-stored patient files that can be used for statistical purposes. There were a few minor drawbacks, including the need for a procedure for training the system to recognize the user's voice.

Chicago↗
PubMed2000

Requirements for speech recognition to support medical documentation.

Recent advances in the development of automated speech recognition (ASR) have made routine applications for medical documentation possible. To achieve this, ASR has to be optimally integrated into the specific documentation scenario. The classification presented in this paper allows the definition of specification requirements. For two different documentation scenarios the appropriate product selection has been done according to this classification. Two evaluation studies are presented, addressing the usefulness of applying automated speech recognition.

Data Collection↗
PubMed2005

An on-line task for contrasting auditory processing in the verbal and nonverbal domains and norms for younger and older adults.

Contrasting linguistic and nonlinguistic processing has been of interest to many researchers with different scientific, theoretical, or clinical questions. However, previous work on this type of comparative analysis and experimentation has been limited. In particular, little is known about the differences and similarities between the perceptual, cognitive, and neural processing of nonverbal environmental sounds and that of speech sounds. With the aim of contrasting verbal and nonverbal processing in the auditory modality, we developed a new on-line measure that can be administered to subjects from different clinical, neurological, or sociocultural groups. This is an on-line task of sound to picture matching, in which the sounds are either environmental sounds or their linguistic equivalents and which is controlled for potential task and item confounds across the two sound types. Here, we describe the design and development of our measure and report norming data for healthy subjects from two different adult age groups: younger adults (18-24 years of age) and older adults (54-78 years of age). We also outline other populations to which the test has been or is being administered. In addition to the results reported here, the test can be useful to other researchers who are interested in systematically contrasting verbal and nonverbal auditory processing in other populations.

Adolescent↗
PubMed2006

Analysis of speech-related variance in rapid event-related fMRI using a time-aware acquisition system.

Speech production introduces signal changes in fMRI data that can mimic or mask the task-induced BOLD response. Rapid event-related designs with variable ISIs address these concerns by minimizing the correlation of task and speech-related signal changes without sacrificing efficiency; however, the increase in residual variance due to speech still decreases statistical power and must be explicitly addressed primarily through post-processing techniques. We investigated the timing, magnitude, and location of speech-related variance in an overt picture naming fMRI study with a rapid event-related design, using a data acquisition system that time-stamped image acquisitions, speech, and a pneumatic belt signal on the same clock. Using a spectral subtraction algorithm to remove scanner gradient noise from recorded speech, we related the timing of speech, stimulus presentation, chest wall movement, and image acquisition. We explored the relationship of an extended speech event time course and respiration on signal variance by performing a series of voxelwise regression analyses. Our results demonstrate that these effects are spatially heterogeneous, but their anatomic locations converge across subjects. Affected locations included basal areas (orbitofrontal, mesial temporal, brainstem), areas adjacent to CSF spaces, and lateral frontal areas. If left unmodeled, speech-related variance can result in regional detection bias that affects some areas critically implicated in language function. The results establish the feasibility of detecting and mitigating speech-related variance in rapid event-related fMRI experiments with single word utterances. They further demonstrate the utility of precise timing information about speech and respiration for this purpose.

Adult↗
PubMed1995

What does voice-processing technology support today?

This paper describes the state of the art in applications of voice-processing technologies. In the first part, technologies concerning the implementation of speech recognition and synthesis algorithms are described. Hardware technologies such as microprocessors and DSPs (digital signal processors) are discussed. Software development environment, which is a key technology in developing applications software, ranging from DSP software to support software also is described. In the second part, the state of the art of algorithms from the standpoint of applications is discussed. Several issues concerning evaluation of speech recognition/synthesis algorithms are covered, as well as issues concerning the robustness of algorithms in adverse conditions.

Algorithms↗
PubMedDate not supplied

Effects of synthetic speech output in the learning of graphic symbols of varied iconicity.

PURPOSE: To examine the effects of additional auditory feedback from synthetic speech on the learning of high translucent symbols versus low translucent symbols. METHOD: Two adults with little or no functional speech and severe intellectual disabilities served as participants. A single-subject ABACA/ACABA design was used to study the relative effects of two treatments: symbol training in the presence and absence of synthetic speech output. RESULTS: The results clearly indicated that the two treatments, rather than extraneous variables were responsible for gains in the symbol learning. Both participants learned either more low translucent symbols or reached their maximum learning of low translucent symbols in the speech output condition. CONCLUSIONS: The results of this preliminary study replicate and extend the iconicity hypothesis to a new set of learning conditions involving speech output, and suggest that feedback from speech output may assist adults with profound intellectual disabilities in coding particularly those symbols whose association with their referent cannot be coded via their visual resemblance with the referent.

Adult↗
PubMed1989

Automatic speech recognition--can it improve the man-machine interface in medical expert systems?

Computer-aided medical diagnosis has existed for two decades, but has not yet attained widespread acceptance among physicians. It is proposed that automatic speech recognition may be a significant factor in the eventual acceptance of the technology by the medical profession. The current state-of-the-art of automatic speech recognition is briefly surveyed, and problems with the technology are discussed. A potential natural language interface with DIAG, an expert system for aiding in dermatologic diagnosis, is described. A system that has been developed for accepting input of body parts in freestyle format is presented as a prototype for a natural language interface with an automatic speech recognition device.

Diagnosis, Computer-Assisted↗
PubMed1986

[Speech input for handicapped patients].

Depending on the remaining functions of the limbs, head, or articulation organs, various types of aids are available to motor impaired persons for controlling technical devices. For those with their speech organs and speaking ability unimpaired, an innovative approach has recently become available through voice input which uses speech recognition to automatically identify spoken input. This mode permits the largest possible information input per time unit, may however involve faulty recognition. Practical applications of speech recognition systems for motor impaired persons lie in the private and occupational settings, with purposes ranging from telecommunication, environmental control, to locomotion or computer control. Examples are the speech-controlled use of a television set or a wheelchair. Apart from controlling technical devices, voice input may, in other disabling conditions, also be employed to aid human communication. An overview of commercial speech recognition devices is given.

Computers↗
PubMed2000

Experience with implementation of a radiology speech recognition system.

Recent advances in speech recognition technology have allowed development of computer systems for real-time radiologist-driven generation of reports. The transition to a speech recognition system is a technically complex process with many potential pitfalls that can decrease efficiency and disrupt workflow. In our recent experience with installation of such a system in an academic radiology department, factors that have worked against optimal performance have included environmental logistics, hardware incompatibilities, radiology information system interface problems, lack of suitable training, and inadequate technical support. Communication of our experience is intended to allow radiologists to anticipate complications of these systems and make informed decisions regarding the feasibility of such a system in their practices. With this information, potential buyers should be able to carefully scrutinize specifications for prospective systems and, by avoiding many of the possible pitfalls, make an easier transition to a speech recognition environment.

Radiology Information Systems↗