TI46 Database Research Articles

System-on-programmable-chip implementation of diminishing learning based pattern recognition system

Support vector machine (SVM) is one of the state-of-the-art tools for linear and nonlinear pattern classification. One of the design issues in SVM classifier is reducing the number of support vectors without compromising the classification accuracy. A technique denoted as diminishing learning (DL) is already proposed in literature for an SVM based multi-class isolated digit recognition system using speaker dependent TI46 database of isolated digits. In this paper, the computational complexity for SVM and SVM-DL based isolated digit recognition system is studied and the computation time for both the classifiers is evaluated by system-on-programmable-chip (SOPC) implementation of the recognition system onto an Altera Cyclone II Series FPGA using Nios II Soft-core processor. The number of support vectors is reduced by 38.28–90.25 % on using SVM-DL for isolated digit recognition problem. This in turn reduces the classification time for SVM-DL by 31.45–91.78 % over SVM. Recognition accuracies of 97 and 98 % are achieved for SVM classifier with and without DL technique, respectively. The study confirms the effect of, the order in which the classes are classified, on the recognition accuracy. For the TI46 database, about 2–4 % increase in recognition accuracy is obtained by choosing the optimum order for SVM-DL classifier. The proposed SOPC implementation of SVM-DL based recognition system can be employed for various other pattern recognition applications too such as face recognition, character recognition and target recognition.

Evaluation of multiclass support vector machine classifiers using optimum threshold-based pruning technique

Support vector machine (SVM) is the state-of-the-art classifier used in real world pattern recognition applications. One of the design objectives of SVM classifiers using non-linear kernels is reducing the number of support vectors without compromising the classification accuracy. To meet this objective, decision-tree approach and pruning techniques are proposed in the literature. In this study, optimum threshold (OT)-based pruning technique is applied to different decision-tree-based SVM classifiers and their performances are compared. In order to assess the performance, SVM-based isolated digit recognition system is implemented. The performances are evaluated by conducting various experiments using speaker-dependent and multispeaker-dependent TI46 database of isolated digits. Based on this study, it is found that the application of OT technique reduces the minimum time required for recognition by a factor of 1.54 and 1.31, respectively, for speaker-dependent and multispeaker-dependent cases. The proposed approach is also applicable for other SVM-based multiclass pattern recognition systems such as target recognition, fingerprint classification, character recognition and face recognition.

Study and evaluation of a multi-class SVM classifier using diminishing learning technique

Support vector machine (SVM) is one of the state-of-the-art tools for linear and non-linear pattern classification. One of the design objectives of an SVM classifier is reducing the number of support vectors without compromising the classification accuracy. For this purpose, a novel technique referred to as diminishing learning (DL) technique is proposed in this paper for a multiclass SVM classifier. In this technique, a sequential classifier is proposed wherein the classes which require stringent boundaries are tested one by one and once the tests for these classes fail, the stringency of the classifier is increasingly relaxed. An automated procedure is also proposed to obtain the optimum classification order for SVM–DL classifier in order to improve the recognition accuracy. The proposed technique is applied for SVM based isolated digit recognition system and is studied using speaker dependent and multispeaker dependent TI46 database of isolated digits. Both LPC and MFCC are used for feature extraction. The features extracted are mapped using self-organized feature maps (SOFM) for dimensionality reduction and the mapped features are used by SVM classifier to evaluate the recognition accuracy using various kernels. The performance of the system using the proposed SVM–DL classifier is compared with those using other techniques: one-against-all (OAA), half-against-half (HAH) and directed acyclic graph (DAG). SVM–DL classifier results in 1–2% increase in recognition accuracy compared to HAH classifier for some of the kernels with both LPC and MFCC feature inputs. For MFCC feature inputs, both HAH and SVM–DL classifiers have 100% recognition accuracy for some of the kernels. The total number of support vectors required is the least for HAH classifier followed by the SVM–DL classifier. The proposed diminishing learning technique is applicable for a number of pattern recognition applications.

Acoustic parameters for automatic detection of nasal manner

Of all the sounds in any language, nasals are the only class of sounds with dominant speech output from the nasal cavity as opposed to the oral cavity. This gives nasals some special properties including presence of zeros in the spectrum, concentration of energy at lower frequencies, higher formant density, higher losses, and stability. In this paper we propose acoustic correlates for the linguistic feature nasal. In particular, we focus on the development of Acoustic Parameters (APs) which can be extracted automatically and reliably in a speaker independent way. These APs were tested in a classification experiment between nasals and semivowels, the two classes of sounds which together form the class of sonorant consonants. Using the proposed APs with a support vector machine based classifier we were able to obtain classification accuracies of 89.53%, 95.80% and 87.82% for prevocalic, postvocalic and intervocalic sonorant consonants respectively on the TIMIT database. As an additional proof to the strength of these parameters, we compared the performance of a Hidden Markov Model (HMM) based system that included the APs for nasals as part of the front-end, with an HMM system that did not. In this digit recognition experiment, we were able to obtain a 60% reduction in error rate on the TI46 database.

Acoustic-phonetic approach to speech recognition based on event detection and linear discriminant analysis

An approach to speech recognition based on phonetic-feature theory was developed to recognize the E-set. The speech signal is first segmented into broad classes based on parameters for the manner phonetic features sonorant, syllabic, continuant, and strident, in addition to silence. The speech signal is divided into the regions: vowel, sonorant consonant, strong fricative, weak fricative, and stop. The events specified by the manner features are then used to extract parameters relevant for the place phonetic features. In particular, we extract parameters for the place phonetic features labial and alveolar for stops; and alveolar and palatal for strong fricatives. Decisions at this stage of recognition are based on an optimal linear combination of parameters. The linear weights are obtained from the training data by applying linear discriminant analysis. The TI46 database is used for training and testing. The results of our event-based system are compared to a standard MFCC and HMM based recognizer. [Work supported by NSF Grant SBR-9729688.]

Improving Speech Recognition Accuracy for Small Vocabulary Applications in Adverse Environments

The problem of improving the accuracy of small vocabulary isolated word speaker dependent speech recognition under adverse conditions such as factory environments is considered. A new approach to solving this problem, by using Output Probability Distributions (OPDs), is presented. OPDs improve the system performance by modelling inter-word relationships, something that a standard maximum likelihood (ML) technique fails to do. The system was tested using the TI46 database, corrupted with the NOISEX-92 database, as well as in a real-world factory environment, and achieved good results.