The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper proposes a hybrid speaker diarization system. The main body is a variational Bayes — hidden Markov model (VB-HMM) speaker diarization system. The VB-HMM speaker diarization system avoids making premature hard decision and takes advantages of soft speaker information in an iterative way. Thus, it outperforms most of mainstream speaker diarization systems. Unfortunately, this system is sensitive...
Massive MIMO and millimeter-wave communication (mmWave) have recently emerged as two key technologies for building 5G wireless networks and beyond. To reconcile the conflict between the large antenna arrays and the limited amount of radio-frequency (RF) chains in mmWave systems, the so-called hybrid beamforming becomes a promising solution and has received a great deal of attention in recent years...
Proxy-word based out of vocabulary (OOV) keyword search has been proven to be quite effective in keyword search. In proxy-word based OOV keyword search, each OOV keyword is assigned several proxies and detections of the proxies are regarded as detections of the OOV keywords. However, the confidence scores of these detections are still those of the proxies from lattices. To obtain a better confidence...
Computational auditory scene analysis (CASA) system is well used in speech enhancement area in recent years. We propose a new system that combines CASA and spectral subtraction to get better enhanced speech. The CASA part consists of the latest method deep neural networks (DNNs). The original way to reconstruct the denoise signal is to use the estimated masks with direct overlap-add method ignoring...
This paper proposes a speech/music classification system based on i-vector. An analysis of two classification methods, namely cosine distance score (CDS) and support vector machine (SVM) is performed. Two session compensation methods, within-class covariance normalization (WCCN) and linear discriminant analysis (LDA) are also discussed. The performance of proposed systems yields better results compared...
End-to-end speech recognition systems have been successfully implemented and have become competitive replacements for hybrid systems. A common loss function to train end-to-end systems is connectionist temporal classification (CTC). This method maximizes the log likelihood between the feature sequence and the associated transcription sequence. However there are some weaknesses with CTC training. The...
Recurrent neural networks (RNNs) have shown an ability to model temporal dependencies. However the problem of exploding or vanishing gradients has limited their application. In recent years, long short-term memory RNNs (LSTM RNNs) have been proposed to solve this problem, and have achieved excellent results. However, because of the large size of LSTM RNNs, they more easily suffer from overfitting,...
At present, the issue of intrusion detection must be a hot point to all over the computer security area. In this paper, two novel intrusion detection techniques have been proposed. First, unlike the current existent detection methods, this paper combines the theories of both intuitionistic fuzzy sets (IFS) and artificial neural networks (ANN) together, which lead to much fewer iteration numbers, higher...
In this paper, we describe the THUEE (Department of Electronic Engineering, Tsinghua University) team's method of building language models (LMs) for the OpenKWS 2015 Evaluation held by the National Institute of Standards and Technology (NIST). Due to the very limited in-domain data provided by NIST, it takes most of our time and efforts to make good use of the out-of-domain data. There are three main...
Speech separation based on deep neural networks (DNNs) has been widely studied recently, and has achieved considerable success. However, previous studies are mostly based on fully-connected neural networks. In order to capture the local information of speech signals, we propose to use convolutional maxout neural networks (CMNNs) to separate speech and noise by estimating the ideal ratio mask of the...
i-Vector modeling has shown to be effective for text independent speaker verification. It represents each utterance as a low-dimensional vector using factor analysis with a GMM supervector. In order to capture more complex speaker statistics, this paper proposes a new feature representation other than i-vectors for speaker verification using neural networks. In this work, stacked bottleneck features...
In this paper, we present a novel framework for handwritten numeral recognition. Considering unconstrained handwritten numerals as numeral feature vectors in the corresponding numeral vector space, we commence by reducing the coordinate dimensionalityof vector space by employing Spectral Regression Discriminant Analysis (SRDA). We then calculate the local density for all numeral classes. For each...
The OpenKWS14 keyword search evaluation is one of the most challenging and influential evaluations in the field of speech recognition. Its goal is to build a high-performance keyword search system for a minority language with limited training data in a short period of time. We present the system of the Department of Electronic Engineering, Tsinghua University (THUEE team) for the OpenKWS14 keyword...
Along with the improvement of equipment reliability, human error has become a great threat to the power system reliability and safety. However, the research of human reliability analysis in power system is still in its infancy. There is still little approach for quantitatively measuring the human reliability of power system. In this paper, the definition of human reliability of power system and a...
Albayzin 2012 language recognition evaluation (LRE) is one of the most challenging language recognition evaluation, which is mainly reflected in: (1) the target languages are more confusable with other languages, which might push down the system performance; (2) developing and test data is heterogeneous regarding duration, number of speakers, ambient noise/music, channel conditions, etc. (3) signals...
In this paper, we propose a method to improve detecting the mispronunciation type of the non-native learners. In order to cope with the low-resource condition of non-native speech and the difference of native and non-native speech, the following efforts are made: 1) train acoustic model with the low-resource non-native data; 2) introduce the articulatory-based tandem feature; 3) pool auxiliary native...
The Context-Dependent Deep-Neural-Network HMM, or CD-DNN-HMM, is a powerful acoustic modeling technique. Its training process typically involves unsupervised pre-training and supervised fine-tuning. In the paper, we demonstrate that the performance of DNNs can be improved by utilizing a large amount of unlabeled data in the training procedure. In our method, CD-DNN-HMM trained using 309 hours of unlabeled...
In prosody event detection field, many local acoustic features have been proposed for representing the prosody characteristics of speech unit. The context information that represents some possible regularities underlying neighboring prosody events, however, hasn't been used effectively. The main difficulty to utilize prosodic context is that it's hard to capture the long-distance sequential dependency...
The Back Propagation (BP) neural network genetic algorithm was used to identify alphabet, and the new algorithm combine the advantages of both genetic algorithm and the BP neural network. Genetic learning algorithm was used for the global optimization and BP training algorithm to accurately optimize the neural network weights and training the neural network to learn letter recognition algorithm. Add-noise...
Audio index is an important part of NIST-RT-SD evaluation since 2003. Speaker Diarization is one kind of audio index technology which is marked by different speakers. One essential component of speaker diarization is speaker clustering which is always the pre-processing of speech recognition. The general method is to extract acoustic feature such as LPCC or MFCC and achieve some model such as HMM...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.