Results Obtained from a Vowel Recognition Computer Program

Forgie, James W.; Forgie, Carma D.

doi:10.1121/1.1936151

Cited by 12 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In designing and implementing our testbed, we looked at the abundance of work towards developing natural user interaction techniques. Some of the key contributions have been: recognizing speech [13], combining pointing with speech [14]; recognizing sign language [15], hand movements [16], and body movements [17]; multimodal mutual disambiguation [18]; and reducing processing of gestures [19]. Recent work that applies some of these techniques can be found in [20]- [23].…”

Section: Related Workmentioning

confidence: 99%

Probabilistic Algorithms, Integration, and Empirical Evaluation for Disambiguating Multiple Selections in Frustum-Based Pointing

Schmidt¹,

Brown²,

Tomlin³

et al. 2006

JMM

View full text Add to dashboard Cite

There are a few fundamental pointing-based user interface techniques for performing selections in 3D environments. One of these techniques is ray pointing, which makes selections by determining intersections of objects along a single ray cast from the user. This technique is susceptible to inaccuracy of the user interface tracking technology and user noise (e.g., jittery hand, see actual viewing ray in Figure 1 (bottom) and how it misses the object when error is factored in). Another technique is the frustum-based (or equivalent cone-based) approach which casts a frustum from the user into the 3D scene. Selections are made by performing intersections of objects with the frustum. This technique resolves the imprecision associated with the ray pointing technique (see how the lightly shaded cone in Figure 1 (bottom) still intersects the object), but may produce multiple ambiguous selections as shown in Figure 2. This paper presents probabilistic selection algorithms and integration schemes that address some of the ambiguities associated with the frustum-based selection technique. The selection algorithms assign probabilities that the user has selected particular objects using a set of low-level 3D intersection-based selection techniques and the relationship of the objects in a hierarchical database. Final selections are generated by integating the outputs from each selection algorithm using one of several weighting schemes. We implemented the selection algoithms and weighting schemes within our distributed augmented reality (AR) and virtual reality (VR) architecture. Next, we performed several experiments to empirically evaluate the probabilistic selection techniques and integration schemes. Our results show that the combined selection and integration algorithms are effective at disambiguating multiple selections. This paper thoroughly describes the architecture, experiments, and results.

show abstract

Section: Related Workmentioning

confidence: 99%

Probabilistic Algorithms, Integration, and Empirical Evaluation for Disambiguating Multiple Selections in Frustum-Based Pointing

Schmidt¹,

Brown²,

Tomlin³

et al. 2006

JMM

View full text Add to dashboard Cite

show abstract

“…Forgie and Forgie [ 5 ] have discussed time duration for recognizing spoken utterances. Hence, the computer was used to determine the time duration of each spoken word.…”

Section: Hz Hz Hzmentioning

confidence: 99%

Word recognition by means of orthogonal functions

Clark

1970

IEEE Trans. Audio Electroacoust.

View full text Add to dashboard Cite

This paper describes experiments in which word recognition is based on comparing the projections of input words on an orthogonal basis with those of a stored library of words. An initial orthogonal basis is determined from the generalized spectrum of short time segments selected from a vocabulary of ten words. The initial basis is optimized by minimizing the complementary error energy. By projecting a spoken word onto the optimum orthogonal basis, a sequence of numbers is generated to represent the word. By correlating the absolute values of the sequence with those of a stored library of words, the spoken word is identifed. The percent of correct recognition varies from 71.6 to 96.6 percent for two speakers.Techniques are developed to improve the recognition scores and to reduce the lengthy computer processing time and large storage requirement. First a master template is made for each word by averaging six templates for the particular word. For one speaker the percent of correct recognition increases to 100 percent when incoming words are compared against the master templates. For a second speaker, the recognition rates improve significantly and vary between 93 and 98 percent when the master templates are used. To further improve the recognition process, the feasibility of grouping words into several classes is demonstrated. The classifications are based on the locations of formant regions and the time durations of each spoken word,

show abstract

“…The earliest attempt to build an ASR system where made in 1950's based on acoustics phonetics. These systems relied on spectral measurements, using spectrum analysis and pattern matching to make recognition decisions on tasks such as vowel recognition [1]. Filter bank analysis was also implemented in some systems to provide spectral information.…”

Section: Introductionmentioning

confidence: 99%

Reconstructed State Space Model for Recognition of Consonant - Vowel (Cv) Utterances Using Support Vector Machines

Narayanan¹

2012

IJAIA

View full text Add to dashboard Cite

This paper presents a study on the use of Support Vector Machines (SVMs) in classifying Malayalam Consonant-Vowel (CV) speech unit by comparing it to two other classification algorithms namely Artificial Neural Network (ANN) and k-Nearest Neighbourhood (k-NN). We extend SVM to combine many two class classifiers into multiclass classifier using Decision Directed Acyclic Graph (DDAG) algorithm. A feature extraction technique using Reconstructed State Space(RSS) based State Space Point Distribution (SSPD) parameters are studied. We obtain an average recognition accuracy of 90% using SSPD for SVM based Malayalam CV speech unit database in speaker independent environments. The result shows that the efficiency of the proposed technique is capable for increasing speaker independent consonant speech recognition accuracy and can be effectively used for developing a complete speech recognition system for Malayalam language.

show abstract

Results Obtained from a Vowel Recognition Computer Program

Cited by 12 publications

References 0 publications

Probabilistic Algorithms, Integration, and Empirical Evaluation for Disambiguating Multiple Selections in Frustum-Based Pointing

Probabilistic Algorithms, Integration, and Empirical Evaluation for Disambiguating Multiple Selections in Frustum-Based Pointing

Word recognition by means of orthogonal functions

Reconstructed State Space Model for Recognition of Consonant - Vowel (Cv) Utterances Using Support Vector Machines

Contact Info

Product

Resources

About