Vocabulary Recognition System Research Articles

Enhanced Optimization in DCNN for Conversion of Non Audible Murmur to Normal Speech based on Dirichlet Process Mixture Feature

In various applications towards mobile communication, the recognition of speech automatically plays a vital role. The user communication devices for interaction require a large amount of vocabulary recognition system, more preciseness and real time less power consuming schemas. The miniaturized battery controlled devices suffer with power consumption and large memory bandwidth. Also the speech challenge people's mobile devices require more attention. Therefore, a useful technology is proposed to convert non-audible murmur to normal speech, based on Stochastic Biogeography-based WOA (SBWOA) integrated with Dirichlet process mixture. The features like spectral skewness, Taylor AMS, spectral centroid, pitch chroma and newly developed Dirichlet Process mixture features are extracted from the input murmured speech signal and trained in the DCNN. The identification of speech is based on Deep Convolutional Neural Network (Deep CNN), which is trained by the proposed Stochastic Biogeography WOA (SBWOA). The stochastic gradient descent method, Biogeography-based optimization (BBO) and Whale optimization algorithm (WOA) are combined together to improve the results in metric analysis. The TRP, FPR and Accuracy shows the improved results of 0.9, 0.001 and 0.99 respectively.

RETRACTED: Application of web embedded system and machine learning in english corpus vocabulary recognition

Built-in applications built on a stand-alone device, TCP / IP network and interconnected are a need for high integration with other systems. The system provided through Web services interconnects service-oriented distributed architecture. The TCP / IP network is widely employed to integrate business applications. This integration is still not provided through the embedded application. The applications connected to the Internet are an especially difficult problem in embedded systems to interpret the sensor data. Real-time sensor function generates a training/classification result for IoT application selected, customized, or data structure design. It has an integrated hardware/software system to achieve the continuous training and real-time data analysis and re-training of Machine Learning (ML) algorithm. World of English native speakers on top of all, this is the database of words that have been separated from the local and non-collection English. It also reported a variety of methods that are used in the English vocabulary recognition system. Please check the study of learners of mediation based on the part of the corpus. Students, in writing, too much-advanced technology and general vocabulary. These students, publicly their discourse in and contributed to the professional corpus of "existence" I mentioned that there is a professional writer, is better. To stimulate the different means of integration, it evaluated several network technology today, discussing the balance between the use of shared with this integration in the adaptability and built-in the field of Web network technology of today.

GMM 지원을 위해 k-means 알고리즘을 이용한 어휘 인식 성능 개선

Abstract General CHMM vocabulary recognition system is model observation probability for vocabulary recognition of recognition rate's low. Used as the limiting unit is applied only to some problem in the phoneme model. Also, they have a problem that does not conform to the needs of the search range to meaning of the words in the vocabulary. Performs a phoneme recognition using GMM to improve these problems. We solve the problem according to the limited search words characterized by an improved k-means algorithm. Measure the effectiveness represented by the accuracy and reproducibility as compared to conventional system performance experiments. Performance test results accuracy is 83%p, and recall is 67%p. Key Words : CHMM(Continuous Hidden Markov Model), GMM(Gaussian Mixture Model), k-means, vocabulary search, vocabulary recognition Received 6 November 2014, Revised 16 December 2014Accepted 20 February 2015Corresponding Author: Lee Jong Sub(The University of Semyung)Email: 99jslee@semyung.ac.krⒸ The Society of Digital Policy & Management. All rights reserved. This is an open-access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0), which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is ISSN: 1738-1916 properly cited.

Reliability measure improvement of Phoneme character extract In Out-of-Vocabulary Rejection Algorithm

Abstract In the communication mobile terminal, Vocabulary recognition system has low recognition rates, because this problems are due to phoneme feature extract from inaccurate vocabulary. Therefore they are not recognize the phoneme and similar phoneme misunderstanding error. To solve this problem, this paper propose the system model, which based on the two step process. First, input phoneme is represent by number which measure the distance of phonemes through phoneme likelihood process. next step is recognize the result through the reliability measure. By this process, we minimize the phoneme misunderstanding error caused by inaccurate vocabulary and perform error correction rate for error provrd vocabulary using phoneme likelihood and reliability. System performance comparison as a result of recognition improve represent 2.7% by method using error pattern learning and semantic pattern. Key Words : Out-of-Vocabulary rejection, Reliability measure, Phoneme Likelihood ※ 이 논문은 2012년도 가천대학교 교내연구비 지원에 의한 결과임 .

Retrieve System for Performance support of Vocabulary Clustering Model In Continuous Vocabulary Recognition System

Abstract Established continuous vocabulary recognition system improved recognition rate by using decision tree based tying modeling method. However, since system model cannot support the retrieve of phoneme data, it is hard to secure the accuracy. In order to improve this problem, we remodeled a system that could retrieve probabilistic model from continuous vocabulary clustering model to phoneme unit. Therefore in this paper showed 95.88%of recognition rate in system performance. Key Words : vocabulary recognition, clustering model, phoneme modeling, tying model, retrieve system ※이 논문은 2012년도 가천대학교 교내연구비 지원에 의한 결과임 .(GCU-2012-R180) * 가천대학교 IT 대학 인터랙티브미디어 교수(교신 저자)논문접수: 2012년 9월 15일, 1차 수정을 거쳐, 심사완료: 2012년 10월 16일 1. 서론 연속 확률 분포 HMM(Hidden Markov Models) 시스템은 어휘 인식률을 높이기 위해 일z반적으로 문맥 종속 모델들과 혼합 가우시안 출력 확률 분포를 이용 한다 [13]. 또한, CHMM(Continuous Hidden Markov Models) 기반 연속 어휘 인식 시스템에서는 어휘 데이터의 효율적인 사용을 위해 공유 방법을 적용한다[11].기존에 사용되는 연속 어휘 클러스터링 모델링은 공유 모델 인식 성능 향상을 위해 Euclidean과 Bhattacharyya 거리 측정을 적용하여 성능 향상을 기존 시스템에 비해 효율적으로 적용하였다[3]. Euclidean 거리 측정은 가중치를 사용하며, 이에 대해 벡터 값을 계산할 때 확률 값이 저하되는 문제점이 있으며, Bhattacharyya 거리 측정은 오류율을 부가적으로 사용하여 계산이 복잡해지고 속도가 느린 단점이 있다. 이러한 단점을 보완하기 위해 Euclidean과 Bhattacharyya 거리 측정을 혼합하고 가우시안 조합에서 가중치를 사용하여 벡터 값을 계산하여 인식 성능을 향상한 방법이 적용되었다. 그러나 이들 시스템에서는 기본적으로 표준화된 어휘 관리와 이들을 라이브러리에 체계적으로 저장하여 검색을 지원하는 시스템을 제공하지 않으므로 어휘의 접근, 검색, 제어를 효율적으로 수행할 수 없다. 이러한 단점을 개선하기 위하여 기존의 연속 어휘 인식 클러스터링 모델에 검색 시스템을 보완하여 인식 성능을 향상시킬 수 있는 시스템을 제안하였다. 본 논문에서 제안하는

Vocabulary Likelihood rate Process support for Recognition rate Improvement of Vocabulary Recognition System

Abstract In the vocabulary recognition model, system has some problems that vocabulary is nor recognize and similar vocabulary recognition is created., because it is caused by system extract vocabulary feature from inaccurate vocabulary. To solve this problems, this paper propose the system modeling and implementation for efficient configuration thread support system, it process the configuration thread information and it apply the facet method in database retrieve for optimization of vocabulary likelihood rate. Proposed system showed 95.31% of vocabulary dependency recognition rate and 97.38% vocabulary independency recognition rate in system performance. Key Words : Vocabulary recognition, configuration thread, vocabulary data, facet, recognition rate ** 본 논문은 2012년 가천대학교의 교내연구비 지원에 의한 결과임(GCU-2012-R202). * 을지대학교 의료 IT 마케팅학과 교수(제1저자) ** 가천대학교 IT대학 인터랙티브미디어학과 교수(교신저자)논문접수: 2012년 10월 25일, 1차 수정을 거쳐, 심사완료: 2012년 11월 20일 1. 서 론 대부분의 어휘 인식 시스템에서는 구현되는 어휘 인식 시스템의 사용 어휘를 미리 지정하고 이에 대한 어휘들을 데이터베이스로 구축하여 사용하고, 이 데이터베이스에서 인식되는 어휘나 어휘 모델을 훈련하게 된다. 이와 같은 어휘 인식 시스템에서는 데이터베이스에 정의된 어휘들은 인식률이 높게 나타나지만 새로운 어휘를 인식할 필요가 있을 때는 다시 모델을 훈련해야 하는 불편함을 가지고 있다.[1][5] 또한, 어휘 인식에서 정보 검색을 위한 영역으로 사용되는 어휘들은 어휘가 간결하고 사용자의 정보 검색을 위한 핵심어로 구성되어진다. 따라서 정보 검색을 위한 영역으로 사용되는 어휘들은 의미적인 분석의 어려움이 따르고 어휘의 오인식으로 인해 문장이 전체적으로 다른 의미를 가지는 단점이 있다[3].본 논문에서 제안한 어휘 인식 시스템에서 입력 어휘는 어휘 유사율 처리를 통해 어휘소 사이의 거리를 측정하여 수치로 나타내고, 인식 결과로부터 오류로 판명되어진 어휘를 확인하여 분류하고 오인식되어진 어휘열은 문법적 어절과 비문법적 어절에 대해 필터링하여 문법적 어절은 인식시키고 비문법적 어절은 오류 보정을 수행한다. 어휘 유사율 처리는 어휘 사이의 거리를 측정하여 비

Building accurate and robust HMM models for practical ASR systems

In this article the relevant training aspects for building robust and accurate HMM models for large vocabulary recognition system are discussed and adjusted, namely: speech features, training steps, and the tying options for context dependent (CD) phonemes. As the basis for building HMM models the well known MASPER training scheme is assumed. First the incorporation of the voicing information and its effect on the classical extraction methods like MFCC and PLP will be shown together with the derivative features, where the relative error reductions are up to 50%. Next the suggested enhancement of the standard training procedure by introducing garbled speech models will be presented and tested on real data. As it will be shown it brings more than a 5% drop in the error rate. Finally, the options for tying states of CD phonemes using decision trees and phoneme classification will be adjusted, tested, and explained.

음절 복원 알고리즘을 이용한 핵심어 오류 보정 시스템

There are two method of error correction in vocabulary recognition system. one error pattern matting base on method other vocabulary mean pattern base on method. They are a failure while semantic of key-word problem for error correction. In improving, in this paper is propose system of key-word error correction using algorithm of syllable restoration. System of key-word error correction by processing of semantic parse through recognized phoneme meaning. It`s performed restore by algorithm of syllable restoration phoneme apply fluctuation before word. It`s definitely parse of key-word and reduced of unrecognized. Find out error correction rate using phoneme likelihood and confidence for system parse. When vocabulary recognition perform error correction for error proved vocabulary. system performance comparison as a result of recognition improve represent 2.3% by method using error pattern learning and error pattern matting, vocabulary mean pattern base on method.

음소 유사율 오류 보정을 이용한 어휘 인식 후처리 시스템

어휘 인식 시스템에서 인식률 저하의 요인으로는 유사한 음소 인식과 부정확한 어휘 제공으로 인해 오인식 오류가 존재한다. 부정확한 어휘의 입력으로 특징을 추출하여 인식할 경우 오인식의 결과가 나타나거나 유사한 음소로 인식되며 특징 추출이 제대로 이루어지지 않으면 음소 인식 시 유사한 음소로 인식하게 된다. 따라서 본 논문에서는 음소가 갖는 특징을 기반으로 음소 유사율을 이용한 어휘 인식 후처리에서의 오류 보정 후처리 시스템을 제안하였다. 음소 유사율은 모노폰으로 훈련시킨 훈련 데이터를 각각의 음소에 MFCC와 LPC 특징 추출 방법을 이용하여 구하였다. 유사한 음소는 정확한 음소로 인식할 수 있도록 유도하여 부정확한 어휘 제공으로 인하여 오인식되는 오류를 최소화하였다. 음소 유사율과 신뢰도를 이용하여 오류 보정율을 구하였으며, 어휘 인식 과정에서 오류로 판명된 어휘에 대하여 오류 보정을 수행하였다. 에러패턴 학습을 이용한 시스템과 의미기반을 이용한 시스템에 비해 시스템 성능 평가 결과 MFCC와 LPC는 각각 7.5%와 5.3%의 인식 향상률을 보였다. In vocabulary recognition system has reduce recognition rate unrecognized error cause of similar phoneme recognition and due to provided inaccurate vocabulary. Input of inaccurate vocabulary by feature extraction case of recognition by appear result of unrecognized or similar phoneme recognized. Also can't feature extraction properly when phoneme recognition is similar phoneme recognition. In this paper propose vocabulary recognition post-process error correction system using phoneme likelihood based on phoneme feature. Phoneme likelihood is monophone training phoneme data by find out using MFCC and LPC feature extraction method. Similar phoneme is induced able to recognition of accurate phoneme due to inaccurate vocabulary provided unrecognized reduced error rate. Find out error correction using phoneme likelihood and confidence when vocabulary recognition perform error correction for error proved vocabulary. System performance comparison as a result of recognition improve represent MFCC 7.5%, LPC 5.3% by system using error pattern and system using semantic.

바타챠랴 거리 측정법을 이용한 음소 유사율 오류 보정 개선 시스템

어휘 인식 시스템은 부정확한 어휘 제공과 유사한 음소 인식으로 인식률이 저하되며 이는 유사한 음소인식 오인식과 효율적 특징 추출 처리를 위한 방법을 필요로 한다. 따라서 본 논문에서는 음소가 갖는 특징을 기반으로 바타챠랴 거리 측정법을 이용한 음소 유사율 오류 보정 개선 시스템을 제안하였다. 음소 유사율은 모노폰으로 훈련시킨 훈련 데이터의 음소에 HMM 특징 추출 방법을 이용하였으며 유사한 음소는 바타챠랴 거리 측정법을 이용하여 정확한 음소로 인식할 수 있도록 유도하여 인식률 향상 효과를 얻을 수 있었다. 이를 유클리디안 거리 측정법과 동적타임 워핑 시스템에 비교한 시스템 성능 평가 결과 1.2%의 향상된 97.91% 인식률을 보였다. Vocabulary recognition system is providing inaccurate vocabulary and similar phoneme recognition due to reduce recognition rate. It's require method of similar phoneme recognition unrecognized and efficient feature extraction process. Therefore in this paper propose phoneme likelihood error correction improvement system using based on phoneme feature Bhattacharyya distance measurement. Phoneme likelihood is monophone training data phoneme using HMM feature extraction method, similar phoneme is induced recognition able to accurate phoneme using Bhattacharyya distance measurement. They are effective recognition rate improvement. System performance comparison as a result of recognition improve represent 1.2%, 97.91% by Euclidean distance measurement and dynamic time warping(DTW) system.

형상 형성 제어를 이용한 어휘인식 공유 모델의 가우시안 최적화

연속 어휘 인식 확률 분포의 공유 방법에서는 사용될 모델 파라미터들의 초기 추정치를 생성하기 위한 각 문맥들에 대한 음소 데이터가 반드시 필요하지만 이들 음소 데이터에 대한 모델을 구성할 수 없는 단점으로 가우시안 모델의 정확성을 확보하지 못한다는 단점이 있다. 이를 개선하기 위하여 확률 분포의 혼합 가우시안 모델을 최적화하고, 음소 단위로 데이터를 탐색을 지원하는 형상 형성 시스템을 제안한다. 본 논문의 형상 형성 시스템은 확장 facet 분류를 이용하여 사용자에게 음소 단위의 형상 형성 정보를 제공하므로 가우시안 모델의 정확성을 제공한다. 본 논문에서 제안한 시스템을 적용한 결과 시스템 성능에서 어휘 종속 인식률은 98.31%, 어휘 독립 인식률은 97.63%의 인식률을 나타내었다. In continuous vocabulary recognition system by probability distribution of clustering method has used model parameters of an advance estimate to generated each contexts for phoneme data surely needed but it has it's bad points of gaussian model the accuracy unsecure of composed model for phoneme data. To improve suggested probability distribution mixed gaussian model to optimized that phoneme data search supported configuration thread system. This paper of configuration thread system has used extension facet classification user phoneme configuration thread information offered gaussian model the accuracy secure. System performance as a result of represent vocabulary dependence recognition rate of 98.31%, vocabulary independence recognition rate of 97.63%.

공유모델 인식 성능 향상을 위한 효율적인 연속 어휘 군집화 모델링

연속 어휘 인식 시스템에서는 통계적 방법에 의한 어휘 인식을 수행하기 위하여 확률분포를 이용하며 이는 음소 단위의클러스터링을사용하여모델링하여샘플들을기반으로 확률 파라미터를 추정한다. 어휘 검색 시 추정된 확률 파라미터로부터 인식 결과를 나타내는데 미리 정의되지 않은 음소와 추가되어진 음소로부터 인식률이 저하되는 문제점이 발생하며, 하나의 클러스터링으로 모델링하므로 가우시안 모델이 정확성을 확보하지 못한다는 단점이 있다. 이를 개선하기 위하여 확률 분포의 혼합 가우시안 모델을 최적화하여 유사도를 기반으로 Euclidean과 Bhattacharyya 거리 측정 방법을 혼합한 군집화 모델을 제안하고, 군집화된 모델에서 음소 단위로 확률 모델을 탐색할 수 있는 시스템을 모델링하였다. 본 논문에서 제안한 시스템을 적용한 결과 시스템 성능에서 어휘 종속 인식률은 98.63%, 어휘 독립 인식률은 97.91%의 인식률을 나타내었다. In continuous vocabulary recognition system by statistical method vocabulary recognition to be performed using probability distribution it also modeling using phoneme clustering for based sample probability parameter presume. When vocabulary search that low recognition rate problem happened in express vocabulary result from presumed probability parameter by not defined phoneme and insert phoneme and it has it's bad points of gaussian model the accuracy unsecure for one clustering modeling. To improve suggested probability distribution mixed gaussian model to optimized for based resemble Euclidean and Bhattacharyya distance measurement method mixed clustering modeling that system modeling for be searching phoneme probability model in clustered model. System performance as a result of represent vocabulary dependence recognition rate of 98.63%, vocabulary independence recognition rate of 97.91%.

The development of the HTK Broadcast News transcription system: An overview

This paper describes in detail the development of the HTK Broadcast News (BN) transcription system and presents full evaluation results from the 1996, 1997 and 1998 DARPA BN evaluations. It starts with a description of the underlying HTK large vocabulary recognition system and presents the modifications used in successive generations of the HTK BN system. Initially acoustic models that relied on fairly precise manual audio-type classification were used. To enable the use of automatic segmentation and classification systems, acoustic models were developed that were independent of fine audio classifications. The basic structure of the current HTK BN system includes a high-quality segmentation stage, multiple decoding passes which initially use triphones and trigrams, and then quinphone acoustic models along with word 4-gram and category language models applied in the final pass. This system gave the lowest error rate in the 1997 BN evaluation by a statistically significant margin. Refinements to the system are then described that examine the use of a larger acoustic training set, vocal tract length normalisation, full variance transforms and improved language modelling. Furthermore a version of the system was developed that ran in less than 10 times real time with only a small increase in error rate which has been used for the bulk transcription of broadcast news for information retrieval from audio data.

MMIE training of large vocabulary recognition systems

This paper describes a framework for optimising the structure and parameters of a continuous density HMM-based large vocabulary recognition system using the Maximum Mutual Information Estimation (MMIE) criterion. To reduce the computational complexity of the MMIE training algorithm, confusable segments of speech are identified and stored as word lattices of alternative utterance hypotheses. An iterative mixture splitting procedure is also employed to adjust the number of mixture components in each state during training such that the optimal balance between the number of parameters and the available training data is achieved. Experiments are presented on various test sets from the Wall Street Journal database using up to 66 hours of acoustic training data. These demonstrate that the use of lattices makes MMIE training practicable for very complex recognition systems and large training sets. Furthermore, the experimental results show that MMIE optimisation of system structure and parameters can yield useful increases in recognition accuracy.

Phoneme based speech recognition

A flexible vocabulary speech recognition system is provided for recognizing speech transmitted via the public switched telephone network. The flexible vocabulary recognition (FVR) system is a phoneme based system. The phonemes are modelled as hidden Markov models. The vocabulary is represented as concatenated phoneme models. The phoneme models are trained using Viterbi training enhanced by: substituting the covariance matrix of given phonemes by others, applying energy level thresholds and voiced, unvoiced, silence labelling constraints during Viterbi training. Specific vocabulary members, such as digits, are represented by allophone models. A* searching of the lexical network is facilitated by providing a reduced network which provides estimate scores used to evaluate the recognition path through the lexical network. Joint recognition and rejection of out-of-vocabulary words are provided by using both cepstrum and LSP parameter vectors.

Vector quantization for speaker adaptation: Results on a 5000-word database

With a view to designing a speaker-independent large vocabulary recognition system, we evaluate a vector quantization approach for speaker adaptation. Only one speaker (the reference speaker) pronounces the application vocabulary. He also pronounces a small vocabulary called the adaptation vocabulary. Each new speaker then merely pronounces the adaptation vocabulary. We have compared two adaptation methods, establishing a correspondence between the codebooks of the reference and the new speakers, on a 20-speaker database with a 104-word application vocabulary. Method I uses a transposed codebook to represent the new speaker during the recognition process, whereas Method II uses a codebook which is obtained by clustering analysis on the NS's pronunciation of the adaptation vocabulary. The adaptation vocabulary contains 136 words. Comparison of the performance of the two methods shows that a new speaker's codebook is not necessary to represent the new speaker. Consequently we have used the first method to perform tests with a 5000-word application vocabulary, and a 4-speaker database. The adaptation is still efficient (the mean improvement is about 14%), even if the relative improvement is 30% compared to 56% obtained in the 104-word application experiment. Further experiments show that the recognition accuracy can be improved by increasing the adaptation vocabulary size and the codebook size.