Speech Feature Parameters Research Articles

A Study on Speech Recognition by a Neural Network Based on English Speech Feature Parameters

In this study, from the perspective of English speech feature parameters, two feature parameters, the mel-frequency cepstral coefficient (MFCC) and filter bank (Fbank), were selected to identify English speech. The algorithms used for recognition employed the classical back-propagation neural network (BPNN), recurrent neural network (RNN), and long short-term memory (LSTM) that were obtained by improving RNN. The three recognition algorithms were compared in the experiments, and the effects of the two feature parameters on the performance of the recognition algorithms were also compared. The LSTM model had the best identification performance among the three neural networks under different experimental environments; the neural network model using the MFCC feature parameter outperformed the neural network using the Fbank feature parameter; the LSTM model had the highest correct rate and the highest speed, while the RNN model ranked second, and the BPNN model ranked worst. The results confirm that the application of the LSTM model in combination with MFCC feature parameter extraction to English speech recognition can achieve higher speech recognition accuracy compared to other neural networks.

A Recognition Method Based on Speech Feature Parameters-English Teaching Practice

In order to improve the effect of English teaching practice, this paper constructs an intelligent English phonetic teaching system combined with the method of phonetic feature parameter recognition. Moreover, this paper simulates the self-mixing interference signal containing noise by establishing a simulation, analyzes the size of the noise and its various possibilities, and selects the EEMD method as the English speech denoising algorithm. In addition, with the support of an intelligent denoising algorithm, this paper implements an English intelligent teaching system based on the recognition algorithm of English speech feature parameters. Finally, this paper evaluates the teaching effect of the intelligent English speech feature recognition algorithm proposed in this paper and the intelligent teaching system of this paper by means of simulation teaching. The research shows that the English teaching system based on the intelligent speech feature recognition algorithm proposed in this paper has a good effect.

Whispered Speech Conversion Based on the Inversion of Mel Frequency Cepstral Coefficient Features

A conversion method based on the inversion of Mel frequency cepstral coefficient (MFCC) features was proposed to convert whispered speech into normal speech. First, the MFCC features of whispered speech and normal speech were extracted and a matching relation between the MFCC feature parameters of whispered speech and normal speech was developed through the Gaussian mixture model (GMM). Then, the MFCC feature parameters of normal speech corresponding to whispered speech were obtained based on the GMM and, finally, whispered speech was converted into normal speech through the inversion of MFCC features. The experimental results showed that the cepstral distortion (CD) of the normal speech converted by the proposed method was 21% less than that of the normal speech converted by the linear predictive coefficient (LPC) features, the mean opinion score (MOS) was 3.56, and a satisfactory outcome in both intelligibility and sound quality was achieved.

The Emotion Recognition System Based on Support Vector Machines

Now speech recognition plays an important role in the filed of human-computer interaction. As the main way to communicate with each other in daily life, voice carries a wealth of emotional information. It is necessary for artificial intelligence to process these information to reach better interaction. In this article, we aim to study a speech emotion recognition system based on support vector machines(SVM), which can recognize different emotions through people’s voice to help people manage their emotions by analysing changes of their emotions. To achieve this goal, we have built a small Chinese voice database including four emotions, each from six different people. We wrote the Matlab program to complete speech feature parameters extraction, model training and emotion recognition, thus realizing the emotion classification of the speech signal.

A Probe into Spoken English Recognition in English Education Based on Computer-Aided Comprehensive Analysis

At present, computer-aided spoken English learning is becoming increasingly popular among learners. The computer-aided comprehensive analysis tech-nology can evaluate and correct learner's spoken pronunciation, thereby im-proving their pronunciation. Based on computer-aided comprehensive analy-sis, this paper aims to explore the automatic recognition and scoring methods of spoken English in English education. For this, it studies the effective matching of the feedback information with the known pronunciation scoring results, and then develops a computer evaluation plug-in consisting of dif-ferent modules such as user login, English spoken speech acquisition and recognition, voice evaluation, speech broadcast, and spoken dialogue. The research results show that the computer evaluation plug-in matches and compares the extracted feature parameters of input speech with the standard features, scores the spoken language input by the learner, and gives the cor-rect pronunciation so that the learner can get feedback in time. For different stages of English learning, the focus of recognition technology and the spo-ken recognition algorithms applied also vary. The research findings provide theoretical and technical support for oral English recognition, error correction and scoring.

The Key Technology of Speech Interaction Based on Deep Learning

Language recognition is essentially a pattern recognition problem, and all kinds of pattern recognition methods are used for language recognition research. For language recognition studied in this project, the highly effective speech feature parameters, acoustic model and language recognition classifier, the Chinese, Tibetan, Mongolian, uygur and training of acoustic model are established, so as to identify the voice input languages. In recent years, the deep learning theory has been applied in the field of speech recognition, and the DNN-HMM model has become the mainstream of acoustic modeling. This project studies Tibetan, Mongolian, Uygur emotion modeling of acoustic model and language model, training methods, studies the decoding algorithm, for continuous speech recognition of input speech, converts it to ethnic Chinese words.

Constructing accurate and robust HMM/GMM models for an Arabic speech recognition system

Conventional Hidden Markov Model (HMM) based Automatic Speech Recognition (ASR) systems generally utilize cepstral features as acoustic observation and phonemes as basic linguistic units. Some of the most powerful features currently used in ASR systems are Mel-Frequency Cepstral Coefficients (MFCCs). Speech recognition is inherently complicated due to the variability in the speech signal which includes within- and across-speaker variability. This leads to several kinds of mismatch between acoustic features and acoustic models and hence degrades the system performance. The sensitivity of MFCCs to speech signal variability motivates many researchers to investigate the use of a new set of speech feature parameters in order to make the acoustic models more robust to this variability and thus improve the system performance. The combination of diverse acoustic feature sets has great potential to enhance the performance of ASR systems. This paper is a part of ongoing research efforts aspiring to build an accurate Arabic ASR system for teaching and learning purposes. It addresses the integration of complementary features into standard HMMs for the purpose to make them more robust and thus improve their recognition accuracies. The complementary features which have been investigated in this work are voiced formants and Pitch in combination with conventional MFCC features. A series of experimentations under various combination strategies were performed to determine which of these integrated features can significantly improve systems performance. The Cambridge HTK tools were used as a development environment of the system and experimental results showed that the error rate was successfully decreased, the achieved results seem very promising, even without using language models.

Seismic facies analysis based on speech recognition feature parameters

Seismic facies analysis plays an important role in seismic stratigraphy. Seismic attributes have been widely applied to seismic facies analysis. One of the most important steps is to optimize the most sensitive attributes with regard to reservoir characteristics. Using different attribute combinations in multidimensional analyses will yield different solutions. Acoustic waves and seismic waves propagating in an elastic medium follow the same law of physics. The generation process of a speech signal based on the acoustic model is similar to the seismic data of the convolution model. We have developed the mel-frequency cepstrum coefficients (MFCCs), which have been successfully applied in speech recognition, as feature parameters for seismic facies analysis. Information about the wavelet and reflection coefficients is well-separated in these cepstrum-domain parameters. Specifically, information about the wavelet mainly appears in the low-domain part, and information about the reflection coefficients mainly appeared in the high-domain part. In the forward model, the seismic MFCCs are used as feature vectors for synthetic data with a noise level of zero and 5%. The Bayesian network is used to classify the traces. Then, classification accuracy rates versus different orders of the MFCCs are obtained. The forwarding results indicate that high accuracy rates are achieved when the order exceeds 10. For the real field data, the seismic data are decomposed into a set of MFCC parameters. The different information is unfolded in the parameter maps, enabling the interpreter to capture the geologic features of the target interval. The geologic features presented in the three instantaneous attributes and coherence can also be found in the MFCC parameter maps. The classification results are in accordance with the paleogeomorphy of the target interval as well as the known wells. The results from the synthetic data and real field data demonstrate the information description abilities of the seismic MFCC parameters. Therefore, using the speech feature parameters to extract information may be helpful for processing and interpreting seismic data.

Reverberant speech recognition combining deep neural networks and deep autoencoders augmented with a phone-class feature

We propose an approach to reverberant speech recognition adopting deep learning in the front-end as well as b a c k-e n d o f a r e v e r b e r a n t s p e e c h r e c o g n i t i o n s y s t e m, a n d a n o v e l m e t h o d t o i m p r o v e t h e d e r e v e r b e r a t i o n p e r f o r m a n c e of the front-end network using phone-class information. At the front-end, we adopt a deep autoencoder (DAE) for enhancing the speech feature parameters, and speech recognition is performed in the back-end using DNN-HMM acoustic models trained on multi-condition data. The system was evaluated through the ASR task in the Reverb Challenge 2014. The DNN-HMM system trained on the multi-condition training set achieved a conspicuously higher word accuracy compared to the MLLR-adapted GMM-HMM system trained on the same data. Furthermore, feature enhancement with the deep autoencoder contributed to the improvement of recognition accuracy especially in the more adverse conditions. While the mapping between reverberant and clean speech in DAE-based dereverberation is conventionally conducted only with the acoustic information, we presume the mapping is also dependent on the phone information. Therefore, we propose a new scheme (pDAE), which augments a phone-class feature to the standard acoustic features as input. Two types of the phone-class feature are investigated. One is the hard recognition result of monophones, and the other is a soft representation derived from the posterior outputs of monophone DNN. The augmented feature in either type results in a significant improvement (7–8 % relative) from the standard DAE.

Speech Feature Parameter Extraction and Recognition Based on Interpolation

The research of the existing speech recognition is based on speech feature parameter, acco-rding to the shortage of poor anti noise and larger storage capacity, etc. So, curve interpolation has been introduced into speech feature parameter extraction to enhance that. Refer to the speech spectrum dynamic changes and the short-time energy smooth stationary characteristics of speech signal, this paper puts forward and designs an arithmetic of speech feature parameter extraction based on interpolation, constructs the feature parameter extraction and personal identification scheme based on speech, and also designs critical modules algorithm. The detail process of feature parameter extraction: firstly, it creates two-dimensional coordinate for each frame data. Then, according to two-dimensional coordinate, it performs Lagrange cubic interpolation for segmentation the data in a signal frame. Get the interpolation coefficient, average the interpolation coefficient for a signal frame, here the average value is seen as the feature parameter for each frame. Lastly, the each frame’s feature parameter is connected in series to form feature parameter of the speech segment. The arithmetic has been simulated an experiment, in order to confirm the applicability and feasibility. The results illustrates the method has preferable anti noise performance, especially expression and storage for overall speech segment feature parameter show more obvious advantages.

A Method of Feature Selection of Voice Content Classification Based on Analysis of Variance in Orthogonal Experiments

In view of the performance of dividing the audio category is closely related to the speech feature parameters selected,a systematic and practical characteristic parameter selection method is presented,orthogonal experimental design method based on analysis of variance.This method has better characteristic [1],the construction of the experiment is simple and the result is easy to analysis,it’s also has directive function to the subsequent experiments.We first do the feture parameters and the level selection,then select amount of appropriate points with representative and typical from a large number of experimental points to construct the orthogonal table to do a analysis of variance by mathematical statistics and orthogonal principle,finding the optimal feature combination. In this pater,the experimental corpus that is voice content is divided into two categories,the kind of traffic and the legal category.Comparing the experimental results shows that the method is not only effective to do feature parameter selection in voice content classification but also has direct meaning to the subsequent experiment design and research.

English Sentence Recognition Based on HMM and Clustering

For English sentences with a large amount of feature data and complex pronunciation changes contrast to words, there are more problems existing in Hidden Markov Model (HMM), such as the computational complexity of the Viterbi algorithm and mixed Gaussian distribution probability. This article explores the segment-mean algorithm for dimensionality reduction of speech feature parameters, the clustering cross-grouping algorithm and the HMM grouping algorithm, which are proposed for the implementation of the speaker-independent English sentence recognition system based on HMM and clustering. The experimental result shows that, compared with the single HMM, it improves not only the recognition rate but also the recognition speed of the system.

Speech Recognition Approach Based on Speech Feature Clustering and HMM

The paper presents a Segment-Mean method for reducing the dimension of the speech feature parameters. K-Means function is used to group the speech feature parameters whose dimension has been reduced. And then the speech samples are classified into different clusters according to their features. It proposes a cross-group training algorithm for the speech feature parameters clustering which improves the accuracy of the clustering function. When recognizing speech, the system uses a cross-group HMM models algorithm to match patterns which reduces the calculation by more than 50% and without reducing the recognition rate of the small vocabulary speech recognition system.

Development of Application Specific Continuous Speech Recognition System in Hindi

Application specific voice interfaces in local languages will go a long way in reaching the benefits of technology to rural India. A continuous speech recognition system in Hindi tailored to aid teaching Geometry in Primary schools is the goal of the work. This paper presents the preliminary work done towards that end. We have used the Mel Frequency Cepstral Coefficients as speech feature parameters and Hidden Markov Modeling to model the acoustic features. Hidden Markov Modeling Tool Kit —3.4 was used both for feature extraction and model generation. The Julius recognizer which is language independent was used for decoding. A speaker independent system is implemented and results are presented.

Application Research of HHT-IF Speech Feature Parameter in Speaker Recognition System

Introduced the Hilbert-Huang transform (HHT) algorithm for nonlinear and non-stationary signal analysis. Specially to non-stationary speech signals, a new method of extracting the speech feature parameters is offered based on the HHT. The speaker identification system is designed based on the VQ and the experiments are carried out at different situations with both HHT-IF and LPCC. The results show that the HHT-IF is feasible for speaker recognition.

Speaker recognition techniques for remote authentication of users in computer networks

This work shows the main characteristics of a system designed to improve security in Internet transactions using a biometric measure: the speech. First, it is given a general overview of the proposed system, developed using Java and C++ programming languages. After that, the main characteristics of the system building blocks are shown, focusing on the techniques for speaker recognition, database, client/server communication and management, and user interface application. The processing load is distributed in this system. The client side is basically responsible for speech acquisition and feature parameters extraction. The server side is responsible for voiceprint generation (on the training phase) or similarity measure between a voiceprint and some feature parameters (on recognition phase). In order to reduce the amount of data transmission, this distributed architecture presents the advantage of transmitting only the feature parameters over the network, instead of the complete wave signal. The acceptance or rejection of a speech identity is based on a pre-defined similarity threshold. Tests using speech database composed of 50 different speakers presented equal error rate (EER) of approximately 1.3%. At the end, the main results obtained from the interaction of the system with several different users are discussed. Besides that, accuracy test results are shown, and future works are addressed.

Speech information processing method and apparatus and storage medium using a segment pitch pattern model

A speech information processing apparatus and method performs speech recognition. Speech is input, and feature parameters of the input speech are extracted. The feature parameters are recognized based on a segment pitch pattern model. The segment pitch pattern model may be obtained by modeling time change in a fundamental frequency of a phoneme belonging to a predetermined phonemic environment with a polynomial segment model. The segment pitch pattern model may also be obtained by modeling with at least one of a single mixed distribution and a multiple mixed distribution.

A feature extraction method using subband based periodicity and aperiodicity decomposition with noise robust frontend processing for automatic speech recognition

This paper proposes a frontend processing technique that employs a speech feature extraction method called Subband based Periodicity and Aperiodicity DEcomposition (SPADE), and examines its validity for automatic speech recognition in noisy environments. SPADE divides speech signals into subband signals, which are then decomposed into their periodic and aperiodic features, and uses both features as speech feature parameters. SPADE employs independent periodicity estimation within each subband and periodicity–aperiodicity decomposition design based on a parallel distributed processing technique motivated by the human speech perception process. Unlike other speech features, this decomposition of speech into two characteristics provides information about periodicities and aperiodicities, and thus allows the utilization of the robustness exhibited by periodic features without losing certain essential information included in aperiodic features. This paper first introduces an implementation of SPADE that operates in the frequency domain, and then examines the validity of combining SPADE with speech enhancement methods. For this examination, we combine SPADE with noise compensation methods that operate in the frequency domain and cepstral normalization methods. In addition, we employ an energy parameter calculation method based on the SPADE framework. An evaluation with the AURORA-2J noisy continuous digit speech recognition database (Japanese AURORA-2) shows that SPADE combined with adaptive Wiener filtering, cepstral normalization, and the energy parameter achieves average word accuracy rates of 82.58% with clean training and 92.55% with multicondition training. These rates are higher than those achieved with ETSI WI008 advanced DSR frontend processing (77.98% and 91.01%, respectively) whose speech feature parameter is based on conventional Mel-frequency cepstral coefficients. By comparison with ETSI WI008 advanced DSR frontend, the proposed method reduces word error rates by 20.9% with clean training and 17.2% with multicondition training. These results confirmed that SPADE combined with noise reduction methods can increase robustness in the presence of noise.

Teager energy based feature parameters for speech recognition in car noise

In this letter, a new set of speech feature parameters based on multirate signal processing and the Teager energy operator is introduced. The speech signal is first divided into nonuniform subbands in mel-scale using a multirate filterbank, then the Teager energies of the subsignals are estimated. Finally, the feature vector is constructed by log-compression and inverse discrete cosine transform (DCT) computation. The new feature parameters have robust speech recognition performance in the presence of car engine noise.

Speech recognition apparatus using syntactic and semantic analysis

A speech recognition apparatus comprises a speech input unit for receiving an input speech signal, analyzing it, and outputting a speech feature parameter series, a speech recognition unit for extracting a speech feature vector from the parameter series, and matching it with a plurality of predetermined words to output a series of word candidates used as keywords, a syntactic analysis unit for analyzing the series of the word candidates as the keywords according to syntactic limitation, and generating a sentence candidate.