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 73 records · Page 4Linked to original sources
PubMed2006

Delay-coordinates embeddings as a data mining tool for denoising speech signals.

In this paper, we utilize techniques from the theory of nonlinear dynamical systems to define a notion of embedding estimators. More specifically, we use delay-coordinates embeddings of sets of coefficients of the measured signal (in some chosen frame) as a data mining tool to separate structures that are likely to be generated by signals belonging to some predetermined data set. We implement the embedding estimator in a windowed Fourier frame, and we apply it to speech signals heavily corrupted by white noise. Our experimental work suggests that, after training on the data sets of interest, these estimators perform well for a variety of white noise processes and noise intensity levels.

Algorithms↗
PubMed2005

Creating accessible science museums with user-activated environmental audio beacons (ping!).

In 2003, Touch Graphics Company carried out research on a new invention that promises to improve accessibility to science museums for visitors who are visually impaired. The system, nicknamed Ping!, allows users to navigate an exhibit area, listen to audio descriptions, and interact with exhibits using a cell phone-based interface. The system relies on computer telephony, and it incorporates a network of wireless environmental audio beacons that can be triggered by users wishing to travel to destinations they choose. User testing indicates that the system is effective, both as a way-finding tool and as a means of providing accessible information on museum content. Follow-up development projects will determine if this approach can be successfully implemented in other settings and for other user populations.

Architectural Accessibility↗
PubMed2006

Factors that influence the performance of experienced speech recognition users.

Performance on automatic speech recognition (ASR) systems for users with physical disabilities varies widely between individuals. The goal of this study was to discover some key factors that account for that variation. Using data from 23 experienced ASR users with physical disabilities, the effect of 20 different independent variables on recognition accuracy and text entry rate with ASR was measured using bivariate and multivariate analyses. The results show that use of appropriate correction strategies had the strongest influence on user performance with ASR. The amount of time the user spent on his or her computer, the user's manual typing speed, and the speed with which the ASR system recognized speech were all positively associated with better performance. The amount or perceived adequacy of ASR training did not have a significant impact on performance for this user group.

Adolescent↗
PubMed2006

The Independent LifeStyle Assistant: lessons learned.

The Independent LifeStyle Assistant (I.L.S.A.) is an agent-based monitoring and support system to help elderly people live longer in their homes by reducing caregiver burden. I.L.S.A. is a multiagent system that incorporates a unified sensing model, situation assessments, response planning, real-time responses, and machine learning. This paper describes the six-month study of the system we fielded in elders' homes and the major lessons we learned during development.

Activities of Daily Living↗
PubMed2006

An interactive voice response (IVR) system for adolescents with alcohol use disorders: a pilot study.

In order to understand predictors of relapse among adolescents treated for alcohol use disorders (AUD), it is important to accurately assess the daily circumstances associated with use. This pilot study investigates the feasibility and acceptability of an interactive voice response (IVR) system in adolescents with AOSUD. Twenty-six adolescents 14 to 19 years old, with a mean age of 16.8, who were enrolled into an adolescent treatment program for AUD consented to make phone calls for 14 successive evenings to an IVR system and answer 14 questions pertaining to daily use of alcohol and other drugs. The subjects were compensated for their participation. A satisfaction questionnaire was administered at the end of the study. Participants completed 72% of scheduled recordings, with an average of 10.1 calls per subject. Most participants reported that they answered the questions honestly and accurately and were very much satisfied with the IVR system. The preliminary data presented here suggests that the use of IVR for the purpose of generating daily reports in youth is feasible and acceptable. The utilization of IVR systems should be explored to improve efficacy and attainment of generalizability to heterogeneous adolescent populations and lifestyles including for other psychiatric disorders.

Adolescent↗
PubMed2005

Utility of a voice-activated system in minimally invasive surgery.

BACKGROUND: Advances in computer enhancements for surgery, including a voice-activated control system for minimally invasive surgery, are being introduced into clinical practice. Few reports have objectively evaluated the utility of the voice-activated control system. The aim of this study was to evaluate the utility of a voice-activated control system for delivery of commands to specific operating room (OR) equipment. MATERIALS AND METHODS: We evaluated a total of 30 laparoscopic procedures: 15 laparoscopic hernia repairs, 10 laparoscopic cholecystectomies, and 5 laparoscopic fundoplications performed with the HERMEStrade mark Operating Room Control Center (Computer Motion, Santa Barbara, California) voice-activated control system. When the voice command (VC) to the HERMES system was given, the circulating nurse was observed and her location was recorded. The 3 locations were A, the nurse was immediately available in the OR, not engaged in any other tasks; B, the nurse was in the OR but engaged in other tasks; or C, the nurse was outside the OR. RESULTS: The 30 cases were performed by the same surgeon and completed laparoscopically. For 170 VCs for gas insufflation, the location of the circulating nurse was: A=50, B=98, and C=22. For 135 light source adjustments, the locations were A=34, B=82, and C=19. In 76 white balance VCs: A=16, B=51, and C=9. In 128 VCs for camera adjustment: A=27, B=77, and C=24. Eight video capture VCs: A=1, B=3, and C=4. For 69 image capture VCs: A=5, B=41, and C=23. The total number of VCs was 586: A=133 (22.7%), B=352 (60%), and C=101(17.3%). All VCs were accurately interpreted by the HERMES system. CONCLUSION: Voice-activated control systems improve communication with and efficiency of OR staff. The surgeon is afforded the most timely equipment adjustment possible. Circulating nurses are allowed to concentrate on patient care instead of equipment adjustment during the course of the surgery.

Humans↗
PubMed2005

Speaker normalization for chinese vowel recognition in cochlear implants.

Because of the limited spectra-temporal resolution associated with cochlear implants, implant patients often have greater difficulty with multitalker speech recognition. The present study investigated whether multitalker speech recognition can be improved by applying speaker normalization techniques to cochlear implant speech processing. Multitalker Chinese vowel recognition was tested with normal-hearing Chinese-speaking subjects listening to a 4-channel cochlear implant simulation, with and without speaker normalization. For each subject, speaker normalization was referenced to the speaker that produced the best recognition performance under conditions without speaker normalization. To match the remaining speakers to this "optimal" output pattern, the overall frequency range of the analysis filter bank was adjusted for each speaker according to the ratio of the mean third formant frequency values between the specific speaker and the reference speaker. Results showed that speaker normalization provided a small but significant improvement in subjects' overall recognition performance. After speaker normalization, subjects' patterns of recognition performance across speakers changed, demonstrating the potential for speaker-dependent effects with the proposed normalization technique.

Artificial Intelligence↗
PubMed2006

Telephony-based voice pathology assessment using automated speech analysis.

A system for remotely detecting vocal fold pathologies using telephone-quality speech is presented. The system uses a linear classifier, processing measurements of pitch perturbation, amplitude perturbation and harmonic-to-noise ratio derived from digitized speech recordings. Voice recordings from the Disordered Voice Database Model 4337 system were used to develop and validate the system. Results show that while a sustained phonation, recorded in a controlled environment, can be classified as normal or pathologic with accuracy of 89.1%, telephone-quality speech can be classified as normal or pathologic with an accuracy of 74.2%, using the same scheme. Amplitude perturbation features prove most robust for telephone-quality speech. The pathologic recordings were then subcategorized into four groups, comprising normal, neuromuscular pathologic, physical pathologic and mixed (neuromuscular with physical) pathologic. A separate classifier was developed for classifying the normal group from each pathologic subcategory. Results show that neuromuscular disorders could be detected remotely with an accuracy of 87%, physical abnormalities with an accuracy of 78% and mixed pathology voice with an accuracy of 61%. This study highlights the real possibility for remote detection and diagnosis of voice pathology.

Algorithms↗
PubMed2006

Multiexpert automatic speech recognition using acoustic and myoelectric signals.

Classification accuracy of conventional automatic speech recognition (ASR) systems can decrease dramatically under acoustically noisy conditions. To improve classification accuracy and increase system robustness a multiexpert ASR system is implemented. In this system, acoustic speech information is supplemented with information from facial myoelectric signals (MES). A new method of combining experts, known as the plausibility method, is employed to combine an acoustic ASR expert and a MES ASR expert. The plausibility method of combining multiple experts, which is based on the mathematical framework of evidence theory, is compared to the Borda count and score-based methods of combination. Acoustic and facial MES data were collected from 5 subjects, using a 10-word vocabulary across an 18-dB range of acoustic noise. As expected the performance of an acoustic expert decreases with increasing acoustic noise; classification accuracies of the acoustic ASR expert are as low as 11.5%. The effect of noise is significantly reduced with the addition of the MES ASR expert. Classification accuracies remain above 78.8% across the 18-dB range of acoustic noise, when the plausibility method is used to combine the opinions of multiple experts. In addition, the plausibility method produced classification accuracies higher than any individual expert at all noise levels, as well as the highest classification accuracies, except at the 9-dB noise level. Using the Borda count and score-based multiexpert systems, classification accuracies are improved relative to the acoustic ASR expert but are as low as 51.5% and 59.5%, respectively.

Algorithms↗
PubMed2006

Discriminative analysis of lip motion features for speaker identification and speech-reading.

There have been several studies that jointly use audio, lip intensity, and lip geometry information for speaker identification and speech-reading applications. This paper proposes using explicit lip motion information, instead of or in addition to lip intensity and/or geometry information, for speaker identification and speech-reading within a unified feature selection and discrimination analysis framework, and addresses two important issues: 1) Is using explicit lip motion information useful, and, 2) if so, what are the best lip motion features for these two applications? The best lip motion features for speaker identification are considered to be those that result in the highest discrimination of individual speakers in a population, whereas for speech-reading, the best features are those providing the highest phoneme/word/phrase recognition rate. Several lip motion feature candidates have been considered including dense motion features within a bounding box about the lip, lip contour motion features, and combination of these with lip shape features. Furthermore, a novel two-stage, spatial, and temporal discrimination analysis is introduced to select the best lip motion features for speaker identification and speech-reading applications. Experimental results using an hidden-Markov-model-based recognition system indicate that using explicit lip motion information provides additional performance gains in both applications, and lip motion features prove more valuable in the case of speech-reading application.

Algorithms↗
PubMed2005

Auditory learning: a developmental method.

Motivated by the human autonomous development process from infancy to adulthood, we have built a robot that develops its cognitive and behavioral skills through real-time interactions with the environment. We call such a robot a developmental robot. In this paper, we present the theory and the architecture to implement a developmental robot and discuss the related techniques that address an array of challenging technical issues. As an application, experimental results on a real robot, self-organizing, autonomous, incremental learner (SAIL), are presented with emphasis on its audition perception and audition-related action generation. In particular, the SAIL robot conducts the auditory learning from unsegmented and unlabeled speech streams without any prior knowledge about the auditory signals, such as the designated language or the phoneme models. Neither available before learning starts are the actions that the robot is expected to perform. SAIL learns the auditory commands and the desired actions from physical contacts with the environment including the trainers.

Algorithms↗
PubMed2005

Experiments with fast Fourier transform, linear predictive and cepstral coefficients in dysarthric speech recognition algorithms using hidden Markov Model.

In this study, a hidden Markov Model was constructed and conditions were investigated that would provide improved performance for a dysarthric speech (isolated word) recognition system. The speaker dependant system was intended to act as an assistive/control tool. A small size vocabulary spoken by three cerebral palsy subjects was chosen. Fast Fourier transform, linear predictive, and Mel frequency cepstral coefficients extracted from data provided training input to several whole-word hidden Markov model configurations. The effect of model structure, number of states, and frame rates were also investigated. It was noted that a 10-state ergodic model using 15 msec frames was better than other configurations. Furthermore, it was found that a Mel cepstrum based model outperformed a fast Fourier transform and linear prediction based model. The system offers effective and robust application as a rehabilitation and/or control tool to assist dysarthric motor impaired individuals.

Algorithms↗
PubMed2007

Performance generalization in biometric authentication using joint user-specific and sample bootstraps.

Biometric authentication performance is often depicted by a detection error trade-off (DET) curve. We show that this curve is dependent on the choice of samples available, the demographic composition and the number of users specific to a database. We propose a two-step bootstrap procedure to take into account the three mentioned sources of variability. This is an extension to the Bolle et al.'s bootstrap subset technique. Preliminary experiments on the NIST2005 and XM2VTS benchmark databases are encouraging, e.g., the average result across all 24 systems evaluated on NIST2005 indicates that one can predict, with more than 75 percent of DET coverage, an unseen DET curve with eight times more users. Furthermore, our finding suggests that with more data available, the confidence intervals become smaller and, hence, more useful.

Algorithms↗
PubMed2005

Ontology-based structured cosine similarity in document summarization: with applications to mobile audio-based knowledge management.

Development of algorithms for automated text categorization in massive text document sets is an important research area of data mining and knowledge discovery. Most of the text-clustering methods were grounded in the term-based measurement of distance or similarity, ignoring the structure of the documents. In this paper, we present a novel method named structured cosine similarity (SCS) that furnishes document clustering with a new way of modeling on document summarization, considering the structure of the documents so as to improve the performance of document clustering in terms of quality, stability, and efficiency. This study was motivated by the problem of clustering speech documents (of no rich document features) attained from the wireless experience oral sharing conducted by mobile workforce of enterprises, fulfilling audio-based knowledge management. In other words, this problem aims to facilitate knowledge acquisition and sharing by speech. The evaluations also show fairly promising results on our method of structured cosine similarity.

Algorithms↗
PubMed2006

On optimizing syntactic pattern recognition using tries and AI-based heuristic-search strategies.

This paper deals with the problem of estimating, using enhanced artificial-intelligence (AI) techniques, a transmitted string X* by processing the corresponding string Y, which is a noisy version of X*. It is assumed that Y contains substitution, insertion, and deletion (SID) errors. The best estimate X+ of X* is defined as that element of a dictionary H that minimizes the generalized Levenshtein distance (GLD) D (X, Y) between X and Y, for all X epsilon H. In this paper, it is shown how to evaluate D (X, Y) for every X epsilon H simultaneously, when the edit distances are general and the maximum number of errors is not given a priori, and when H is stored as a trie. A new scheme called clustered beam search (CBS) is first introduced, which is a heuristic-based search approach that enhances the well-known beam-search (BS) techniques used in AI. The new scheme is then applied to the approximate string-matching problem when the dictionary is stored as a trie. The new technique is compared with the benchmark depth-first search (DFS) trie-based technique (with respect to time and accuracy) using large and small dictionaries. The results demonstrate a marked improvement of up to 75% with respect to the total number of operations needed on three benchmark dictionaries, while yielding an accuracy comparable to the optimal. Experiments are also done to show the benefits of the CBS over the BS when the search is done on the trie. The results also demonstrate a marked improvement (more than 91%) for large dictionaries.

Algorithms↗
PubMed2006

Real-time face detection and lip feature extraction using field-programmable gate arrays.

This paper proposes a new technique for face detection and lip feature extraction. A real-time field-programmable gate array (FPGA) implementation of the two proposed techniques is also presented. Face detection is based on a naive Bayes classifier that classifies an edge-extracted representation of an image. Using edge representation significantly reduces the model's size to only 5184 B, which is 2417 times smaller than a comparable statistical modeling technique, while achieving an 86.6% correct detection rate under various lighting conditions. Lip feature extraction uses the contrast around the lip contour to extract the height and width of the mouth, metrics that are useful for speech filtering. The proposed FPGA system occupies only 15050 logic cells, or about six times less than a current comparable FPGA face detection system.

Artificial Intelligence↗