Isolated Word Recognition Research Articles

Robust feature extraction from spectrum estimated using bispectrum for speaker recognition

Extraction of robust features from noisy speech signals is one of the challenging problems in Automatic Speech Recognition (ASR). For Gaussian process, its bispectrum and all higher order spectra are identically zero, which means that bispectrum removes the additive white Gaussian noise while preserving the magnitude and phase information of original signal. Using this bispectrum property, spectrum of original signal can be recovered from its noisy version. Robust Mel Frequency Cepstral Coefficients (MFCC) are extracted from the estimated spectral magnitude (denoted as Bispectral-MFCC (BMFCC)). The effectiveness of BMFCC has been tested on TI-46 isolated word database in noisy (additive white Gaussian) environment. The experimental results show the superiority of the proposed technique over conventional methods for Isolated Word Recognition (IWR).

음성인식 로봇을 위한 동시통화검출 기반의 강인한 음성 끝점 검출

본 논문에서는 반향이 큰 로봇 환경에 강인한 음성 끝점 검출 방법을 제안한다. 양방향 대화 로봇과 같이 반향대 신호 비가 -5 dB 이하인 반향환경에서는, 반향제거기의 성능이 저하되어 사용자 음성 에너지와 비슷한 크기의 에너지를 갖는 잔여반향이 생긴다. 잡음에 강인한 기존의 음성 끝점검출 방법이라도, 사용자 음성과 비슷한 수준의 에너지를 갖는 잔여반향은 음성으로 오검출하기 때문에 정확한 음성 끝점검출이 어렵다. 반향 환경에 강인한 끝점검출을 위해, 본 논문에서는 음성/반향 구간 판별에 좋은 성능을 보이는 동시통화검출의 결과를 기존의 음성끝점검출 방법과 AND 연산하여 음성끝점검출기를 구성하였다. 제안하는 방법의 평가를 위해 반향이 큰 환경에서 고립단어 인식을 실험하였고, 다양한 실험환경에서 기존 음성 끝점검출 방법보다 평균 30 % 이상의 인식 성능 향상을 확인할 수 있었다. This paper presents a robust speech end-point detector using double talk detection in echoic conditioned speech recognition robot. The proposed method consists of combining conventional end-point detector result and double talk detector result. We have tested the proposed method in isolated word recognition system under echoic conditioned environment. As a result, the proposed algorithm shows superior performance of 30 % to the available techniques in the points of speech recognition rates.

Isolated Word Recognition Using Ergodic Hidden Markov Models and Genetic Algorithm

Isolated Word Recognition Using Ergodic Hidden Markov Models and Genetic Algorithm

Isolated Word Recognition Using Ergodic Hidden Markov Models and Genetic Algorithm

Speech to text was one of speech recognition applications which speech signal was processed, recognized and converted into a textual representation. Hidden Markov model (HMM) was the widely used method in speech recognition . However, the level of accuracy using HMM was strongly influenced by the optimalization of extraction process and modellling methods . Hence in this research, the use of genetic algorithm (GA) method to optimize the Ergodic HMM was tested. In Hybrid HMM-GA, GA was used to optimize the Baum-Welch method in the training process. It was useful to improve the accuracy of the recognition result which is produced by the HMM parameters that generate the low accuracy when the HMM are tested. Based on the research, the percentage increases the level of accuracy of 20% to 41%. Proved that the combination of GA in HMM method can gives more optimal results when compared with the HMM system that not combine with any method.

Isolated Word Recognition Using Ergodic Hidden Markov Models and Genetic Algorithm

Speech to Text was one of speech recognition applications which speech signal was processed, recognized and converted into a textual representation. Hidden Markov Model (HMM) was the widely used method in speech recognition. However, the level of accuracy using HMM was strongly influenced by the optimalization of extraction process and modellling methods. Hence in this research, the use of genetic algorithm (GA) method to optimize the Ergodic HMM was tested. In Hybrid HMM-GA, GA was used to optimize the Baum-welch method in the training process. It was useful to improve the accuracy of the recognition result which is produced by the HMM parameters that generate the low accuracy when the HMM are tested. Based on the research, the percentage increases the level of accuracy of 20% to 41%. Proved that the combination of GA in HMM method can gives more optimal results when compared with the HMM system that not combine with any method.

Small-vocabulary speech recognition using a silent speech interface based on magnetic sensing

This paper reports on word recognition experiments using a silent speech interface based on magnetic sensing of articulator movements. A magnetic field was generated by permanent magnet pellets fixed to relevant speech articulators. Magnetic field sensors mounted on a wearable frame measured the fluctuations of the magnetic field during speech articulation. These sensor data were used in place of conventional acoustic features for the training of hidden Markov models. Both small vocabulary isolated word recognition and connected digit recognition experiments are presented. Their results demonstrate the ability of the system to capture phonetic detail at a level that is surprising for a device without any direct access to voicing information.

Effects of age and hearing loss on the recognition of interrupted words in isolation and in sentences

The ability to recognize spoken words interrupted by silence was investigated with young normal-hearing listeners and older listeners with and without hearing impairment. Target words from the revised SPIN test by Bilger et al. [J. Speech Hear. Res. 27(1), 32-48 (1984)] were presented in isolation and in the original sentence context using a range of interruption patterns in which portions of speech were replaced with silence. The number of auditory "glimpses" of speech and the glimpse proportion (total duration glimpsed/word duration) were varied using a subset of the SPIN target words that ranged in duration from 300 to 600 ms. The words were presented in isolation, in the context of low-predictability (LP) sentences, and in high-predictability (HP) sentences. The glimpse proportion was found to have a strong influence on word recognition, with relatively little influence of the number of glimpses, glimpse duration, or glimpse rate. Although older listeners tended to recognize fewer interrupted words, there was considerable overlap in recognition scores across listener groups in all conditions, and all groups were affected by interruption parameters and context in much the same way.

Electrophysiological correlates of morphosyntactic integration in German phrasal context

The morphosyntactic paradigm of an inflected word can influence isolated word recognition, but its role in multiple-word phrasal integration is less clear. We examined the electrophysiological response to adjectives in short German prepositional phrases to evaluate whether strong and weak forms of the adjective show a differential response, and whether paradigm variables are related to this response. Twenty native German speakers classified serially presented phrases as grammatically correct or not while the electroencephalogram (EEG) was recorded. A functional mixed effects model of the response to grammatically correct trials revealed a differential response to strong and weak forms of the adjectives. This response difference depended on whether the preceding preposition imposed accusative or dative case. The lexically conditioned information content of the adjectives modulated a later interval of the response. The results indicate that grammatical context modulates the response to morphosyntactic information content, and lends support to the role of paradigm structure in integrative phrasal processing.

DWT and LPC based feature extraction methods for isolated word recognition

In this article, new feature extraction methods, which utilize wavelet decomposition and reduced order linear predictive coding (LPC) coefficients, have been proposed for speech recognition. The coefficients have been derived from the speech frames decomposed using discrete wavelet transform. LPC coefficients derived from subband decomposition (abbreviated as WLPC) of speech frame provide better representation than modeling the frame directly. The WLPC coefficients have been further normalized in cepstrum domain to get new set of features denoted as wavelet subband cepstral mean normalized features. The proposed approaches provide effective (better recognition rate), efficient (reduced feature vector dimension), and noise robust features. The performance of these techniques have been evaluated on the TI-46 isolated word database and own created Marathi digits database in a white noise environment using the continuous density hidden Markov model. The experimental results also show the superiority of the proposed techniques over the conventional methods like linear predictive cepstral coefficients, Mel-frequency cepstral coefficients, spectral subtraction, and cepstral mean normalization in presence of additive white Gaussian noise.

A robust feature extraction approach based on an auditory model for classification of speech and expressiveness

Based on an auditory model, the zero-crossings with maximal Teager energy operator (ZCMT) feature extraction approach was described, and then applied to speech and emotion recognition. Three kinds of experiments were carried out. The first kind consists of isolated word recognition experiments in neutral (non-emotional) speech. The results show that the ZCMT approach effectively improves the recognition accuracy by 3.47% in average compared with the Teager energy operator (TEO). Thus, ZCMT feature can be considered as a noise-robust feature for speech recognition. The second kind consists of mono-lingual emotion recognition experiments by using the Taiyuan University of Technology (TYUT) and the Berlin databases. As the average recognition rate of ZCMT approach is 82.19%, the results indicate that the ZCMT features can characterize speech emotions in an effective way. The third kind consists of cross-lingual experiments with three languages. As the accuracy of ZCMT approach only reduced by 1.45%, the results indicate that the ZCMT features can characterize emotions in a language independent way.

Bilingual word recognition in a sentence context.

This article provides an overview of bilingualism research on visual word recognition in isolation and in sentence context. Many studies investigating the processing of words out-of-context have shown that lexical representations from both languages are activated when reading in one language (language-non-selective lexical access). A newly developed research line asks whether language-non-selective access generalizes to word recognition in sentence contexts, providing a language cue and/or semantic constraint information for upcoming words. Recent studies suggest that the language of the preceding words is insufficient to restrict lexical access to words of the target language, even when reading in the native language. Eye tracking studies revealing the time course of word activation further showed that semantic constraint does not restrict language-non-selective access at early reading stages, but there is evidence that it has a relatively late effect. The theoretical implications for theories of bilingual word recognition are discussed in light of the Bilingual Interactive Activation+ model (Dijkstra and van Heuven, 2002).

Isolated Word Command Recognition for Robot Navigation

This project is demonstrating Robot Navigation Control using Isolated Word Recognition. Five spoken word commands (Go, Stop, Left, Right and Back) should be record and used as commands. Fast Fourier Transform (FFT) is used to filter the noise by creating butter worth filter. The noise cancelation method is then used to make the software sensitive and recognize the word Normalization, Power density spectrum and voice fingerprint method are used and implemented by MATLAB programming code. Then the command signal of recognized word is sent via XBee, wireless connection to robot. The robot will receive and response to the spoken command signal by a PIC microcontroller which will control the robot movement.

A VLSI Architecture with Multiple Fast Store-Based Block Parallel Processing for Output Probability and Likelihood Score Computations in HMM-Based Isolated Word Recognition

This paper presents a memory-efficient VLSI architecture for output probability computations (OPCs) of continuous hidden Markov models (HMMs) and likelihood score computations (LSCs). These computations are the most time consuming part of HMM-based isolated word recognition systems. We demonstrate multiple fast store-based block parallel processing (MultipleFastStoreBPP) for OPCs and LSCs and present a VLSI architecture that supports it. Compared with conventional fast store-based block parallel processing (FastStoreBPP) and stream-based block parallel processing (StreamBPP) architectures, the proposed architecture requires fewer registers and less processing time. The processing elements (PEs) used in the FastStoreBPP and StreamBPP architectures are identical to those used in the MultipleFastStoreBPP architecture. From a VLSI architectural viewpoint, a comparison shows that the proposed architecture is an improvement over the others, through efficient use of PEs and registers for storing input feature vectors.

An Experimental Study on Dynamic Features of Speech Structure

One of the biggest difficultiesin automatic speech recognition (ASR) is how to deal with variations of speech signals caused by non-linguistic information, such as age, gender, etc. Various methods have been proposed to compensate for the variations and one of them is speech structure [1]. Speech structure, which extracts only contrastive features and discards absolute features, is proved to be transform-invariant mathematically and to be very robust with the non-linguistic variations experimentally [2]. Although the conventional speech structure extracts local and distant contrastive features, it did not extract dynamic features explicitly which are supposed to exist in the contrastive features. In this paper, we reformulate speech structure based on trajectory HMM and derive trajectory structure (TSR), in which dynamic and contrastive features can be defined and used in ASR. We carry out an experiment of n-best rescoring of isolated word recognition using trajectory structure and obtain 28.5% relative decrease in word error rate.

Substitution Error Analysis for Improving the Word Accuracy in Telugu Language Automatic Speech Recognition System

Use of natural languages for the computer communication is one of the current research topics. The speech recognition plays a central role in communicating the computer by means of speech. Speech Recognition is the process of converting analog signal into the symbolic gesture form known as text. An Automatic Speech Recognition (ASR) is the process of converting input speech signal given to the system, into text. This input signal is any human spoken word. Though the last Four decades, research is going on bringing the system perception near to the human being, in recognition word accuracy. Many domains play a role in degrading the of system performance in which language and its pronunciation variants caused by different reasons like accent, gender, dialects of the speech are in general factors. In specific, system environment, articulatory phonetics, acoustic phonetics, (acoustic system), lexical model (pronunciation dictionary) and language model including the mood of the speaker. Acoustic modeling can be done in most of the cases by using signal processing, where as lexicon model require a sufficient human intervention as, it is based on the language and human perception. Once sufficient primary data is built then automatic processing can be done using different modeling techniques to derive more data for proper training of the speech recognition system. Here the linguistics are play a major role in building the robust system. In lexical model design language plays a major role. Each language has its own rhythm in speech and language aspects. Based on language rhythm worldly languages are classified as stress timed and syllable timed rhythm. Most of ASR systems use the lexical model that is built for stressed timed languages. All Indian languages are syllable timed rhythmic languages one such is Telugu Language. In this paper analysis of the decoding results of ASR system using two different lexical model environments. One is CMU lexicon which is based on stress timed language as the tool is used American accent English phonemes and another UOH lexicon which is handcraft lexicon for Telugu language which is also a syllable timed language.. Further studied are the gender and accents (pronunciation variant factors) effecting the Substitutional errors in ASR system. The confusion matrix for vowel and consonants alone analyzed for both cases and also for isolated word recognition where the confusion matrix gives the most common phonemes substituted. In all the cases the UOH lexicon based ASR system gives the improvement of word accuracy around 20 to 30%. Speech is a process used to communicate from a speaker to listener. Pronunciation relates to speech, and humans have an intuitive feel for pronunciation. For instance, people chuckle when words are mispronounced and notice when foreign accent colors a speaker's pronunciations.(1). If the words were always pronounced in the same way, ASR would be relatively easy. However, for various reasons words are almost always pronounced differently and varied from one speaker to another and from once situation to another. The variability is due to co-articulation, reasonal accents, speaking rate, speaking style etc.

Validating Craft Knowledge

This longitudinal study investigated children's performance on several informal reading and spelling tasks. Students (n = 274) in a rural North Carolina county were assessed across grades 2 to 6 on the following measures: isolated word recognition (timed and untimed), oral reading accuracy, reading comprehension, reading rate, and spelling. Statistics (means and standard deviations) were reported for each measure each year. Overall, the results tended to support traditional performance criteria in reading diagnosis. Two findings that deserve further study were (1) word recognition–timed proved to be a good predictor of oral reading rate at each grade level (median r = .68), and (2) both oral and silent reading rates, after increasing steadily from grade 2 to 4, began to taper off between grades 4 and 6. This second finding is in contrast to previous reading-rate data reported by Hasbrouck and Tindal and by Taylor.

레벤스타인 거리 기반의 위치 정확도를 이용하여 다중 음성 인식 결과에서 관련성이 적은 후보 제거

Many isolated word recognition systems may generate irrelevant words for recognition results because they use only acoustic information or small amount of language information. In this paper, I propose word similarity that is used for selecting (or removing) less common words from candidates by applying Levenshtein distance. Word similarity is obtained by using positional accuracy that reflects the frequency information along to character's alignment information. This paper also discusses various improving techniques of selection of disparate words. The methods include different loss values, phone accuracy based on confusion information, weights of candidates by ranking order and partial comparisons. Through experiments, I found that the proposed methods are effective for removing heterogeneous words without loss of performance.

참조화자로부터 추정된 적응적 혼성 사전분포를 이용한 MAPLR 고속 화자적응

본 논문은 maximum a posteriori linear regression (MAPLR) 기반의 고속 화자적응 성능을 개선하기 위하여 사전분포를 추정하는 두 가지 방식을 제안한다. 일반적으로 MAPLR 방식에서 사용되는 변환행렬의 사전분포는 화자독립모델을 구성하는 훈련 화자들로부터 추정되어 모든 화자들에게 동등하게 적용된다. 본 논문에서는 새로운 화자에게 보다 더 적합한 사전분포를 적용하고자 적응 데이터를 이용하여 새로운 화자의 음향특성과 가까운 참조화자 집단을 선택한 후 참조화자 집단으로부터 사전분포를 추정하는 방법을 제안한다. 또한, 블록 대각 형태의 변환행렬의 사전분포를 추정하는 경우 사전분포의 평균행렬과 공분산행렬을 동일한 훈련 화자들로부터 얻어진 두 가지 형태의 변환행렬집단으로부터 각각 추정하는 방법을 제안한다. 제안된 방법의 성능 평가를 위하여 고립단어 인식실험을 통해 적응 단어의 개수에 따른 단어 인식률을 평가한다. 실험결과, 적응 단어 수가 매우 적을 때 기존의 MAPLR 방식에 비하여 통계적으로 유의미한 성능향상이 얻어짐을 보여준다. This paper proposes two methods of estimating prior distribution to improve the performance of rapid speaker adaptation based on maximum a posteriori linear regression (MAPLR). In general, prior distribution of the transformation matrix used in MAPLR adaptation is estimated from all of the training speakers who are employed to construct the speaker-independent model, and it is applied identically to all new speakers. In this paper, we propose a method in which prior distribution is estimated from a group of reference speakers, selected using adaptation data, so that the acoustic characteristics of the selected reference speakers may be similar to that of the new speaker. Additionally, in MAPLR adaptation with block-diagonal transformation matrix, we propose a method in which the mean matrix and covariance matrix of prior distribution are estimated from two groups of transformation matrices obtained from the same training speakers, respectively. To evaluate the performance of the proposed methods, we examine word accuracy according to the number of adaptation words in the isolated word recognition task. Experimental results show that, for very limited adaptation data, statistically significant performance improvement is obtained in comparison with the conventional MAPLR adaptation.

American Sign Language word recognition with a sensory glove using artificial neural networks

An American Sign Language (ASL) recognition system is being developed using artificial neural networks (ANNs) to translate ASL words into English. The system uses a sensory glove called the Cyberglove™ and a Flock of Birds ® 3-D motion tracker to extract the gesture features. The data regarding finger joint angles obtained from strain gauges in the sensory glove define the hand shape, while the data from the tracker describe the trajectory of hand movements. The data from these devices are processed by a velocity network with noise reduction and feature extraction and by a word recognition network. Some global and local features are extracted for each ASL word. A neural network is used as a classifier of this feature vector. Our goal is to continuously recognize ASL signs using these devices in real time. We trained and tested the ANN model for 50 ASL words with a different number of samples for every word. The test results show that our feature vector extraction method and neural networks can be used successfully for isolated word recognition. This system is flexible and open for future extension.

Parallel Reservoir Computing Using Optical Amplifiers

Reservoir computing (RC), a computational paradigm inspired on neural systems, has become increasingly popular in recent years for solving a variety of complex recognition and classification problems. Thus far, most implementations have been software-based, limiting their speed and power efficiency. Integrated photonics offers the potential for a fast, power efficient and massively parallel hardware implementation. We have previously proposed a network of coupled semiconductor optical amplifiers as an interesting test case for such a hardware implementation. In this paper, we investigate the important design parameters and the consequences of process variations through simulations. We use an isolated word recognition task with babble noise to evaluate the performance of the photonic reservoirs with respect to traditional software reservoir implementations, which are based on leaky hyperbolic tangent functions. Our results show that the use of coherent light in a well-tuned reservoir architecture offers significant performance benefits. The most important design parameters are the delay and the phase shift in the system's physical connections. With optimized values for these parameters, coherent semiconductor optical amplifier (SOA) reservoirs can achieve better results than traditional simulated reservoirs. We also show that process variations hardly degrade the performance, but amplifier noise can be detrimental. This effect must therefore be taken into account when designing SOA-based RC implementations.