Serwis Infona wykorzystuje pliki cookies (ciasteczka). Są to wartości tekstowe, zapamiętywane przez przeglądarkę na urządzeniu użytkownika. Nasz serwis ma dostęp do tych wartości oraz wykorzystuje je do zapamiętania danych dotyczących użytkownika, takich jak np. ustawienia (typu widok ekranu, wybór języka interfejsu), zapamiętanie zalogowania. Korzystanie z serwisu Infona oznacza zgodę na zapis informacji i ich wykorzystanie dla celów korzytania z serwisu. Więcej informacji można znaleźć w Polityce prywatności oraz Regulaminie serwisu. Zamknięcie tego okienka potwierdza zapoznanie się z informacją o plikach cookies, akceptację polityki prywatności i regulaminu oraz sposobu wykorzystywania plików cookies w serwisie. Możesz zmienić ustawienia obsługi cookies w swojej przeglądarce.
In this paper, two models, the I-vector and the Gaussian Mixture Model-Universal Background Model (GMM-UBM), are compared for the speaker identification task. Four feature combinations of I-vectors with seven fusion techniques are considered: maximum, mean, weighted sum, cumulative, interleaving and concatenated for both two and four features. In addition, an Extreme Learning Machine (ELM) is exploited...
Point Process Models (PPM) have been widely used for keyword spotting applications. Training these models typically requires a considerable number of keyword examples. In this work, we consider a scenario where very few keyword examples are available for training. The availability of a limited number of training examples results in a PPM with poorly learnt parameters. We propose an unsupervised online...
The vulnerability of automatic speaker verification (ASV) systems against spoofing attacks is an important security concern about the reliability of ASV technology. Recently, various countermeasures have been developed for spoofing detection. In this paper, we propose to use features derived from linear prediction (LP) residual signal for spoofing detection using simple Gaussian mixture model (GMM)...
In this paper, the development of Multilingual Phone Recognition System (MPRS) in the context of Indian languages is described. MPRS is a language independent Phone Recognition System (PRS) that could recognise the phonetic units present in a speech utterance of any language. We have developed two Bilingual and a quadrilingual PRS using four Indian languages — Kannada, Telugu, Bengali, and Odia. International...
With the rapid development of Internet, how to obtain valuable information from massive messages has become a major problem we need to be solved in the information explosive era. This paper introduces the development route of information extraction technology, and discusses four categories of Chinese entity relation extraction technologies in depth. Finally, the advantages and disadvantages of different...
Deep neural networks (DNN) have recently been shown to give state-of-the-art performance in monaural speech enhancement. However in the DNN training process, the perceptual difference between different components of the DNN output is not fully exploited, where equal importance is often assumed. To address this limitation, we have proposed a new perceptually-weighted objective function within a feedforward...
Background noise reduction has been studied for many years. However, unwanted human speech noise suppression is not well discussed due to sparsity of the speech signal. Traditional blind source separation (BSS) methods such as independent component analysis (ICA) assume the prior knowledge of the number of sources and require that the number of sources must equal the number of sensors. Above limitations...
The article presents studies on the automatic whispery speech recognition. In the performed research a new corpus with whispery speech has been used. The aim of studies presented in this paper was to check, how the vocabulary size and the language model order influence on the speech recognition quality. It has been concluded that even using recordings with 5,000 different words only it is possible...
A large amount of parallel training corpus is necessary for robust, high-quality voice conversion. However, such parallel data may not always be available. This letter presents a new voice conversion method that needs no parallel speech corpus, and adopts a restricted Boltzmann machine (RBM) to represent the distribution of the spectral features derived from a target speaker. A linear transformation...
Speaker recognition has been developed over many years and it comes with many different methods. MFCC is one of more the successful methods due to it being generally modeled on the human auditory system. It represents high success rate of recognition and strong robustness against noise in the lower frequency regions. However, in the higher frequency regions, it captures speaker characteristics information...
In this paper, we present a novel spectrum mapping method — Continuous Frequency Warping and Magnitude Scaling (CFWMS) for voice conversion under the Joint Density Gaussian Mixture Model (JDGMM) framework. JDGMM is a mature clustering technique that models the joint probability density of speech signals from paired speakers. The conventional JDGMM-based approaches morph the spectral features via least...
In the paper we investigate the performance of parallel deep neural network training with parameter averaging for acoustic modeling in Kaldi, a popular automatic speech recognition toolkit. We describe experiments based on training a recurrent neural network with 4 layers of 800 LSTM hidden states on a 100-hour corpora of annotated Polish speech data. We propose a MPI-based modification of the training...
Factor of sparsity in a speech signal plays an important role in the speech processing. This paper proposed a method in which variable regularization factor of sparsity is applied for the mixed signal and used to separate the monaural speech signals. The sparsity regularization factor for individual training and testing signal was find using particle swarm optimization. Algorithm has been tested for...
A much discussed topic in the recent years is the interconnectedness of industrial plants in the field of Cyber-Physical Production Systems (CPPS). In the future, the data and aggregated information from various production plants will be available globally at any time. Particularly in maintenance, this could be a helpful information expansion for the maintenance staff, since maintenance information...
This paper describes the implementation of HMM (Hidden Markov Model) based speaker independent isolated word Automatic Speech Recognition (ASR) system for Nepali Language, a commonly spoken language in Nepal. The system has been developed in python using numpy[1] and YAHMM[2] libraries. The system is trained in different Nepali words by collecting data from different speakers in room environment....
Performances of some training techniques of automatic speech recognition system are compared in this paper. Speech recognition accuracy was used as measure of performance. Different kinds of outdoor and indoor noise were used for studying. It is shown the superiority of training on noised speech methods over the competitive technique of training on clear speech. It has been found that training by...
Deep learning has brought a breakthrough to the performance of speech recognition. The speech recognition systems based on deep neural networks have obtained the state-of-the-art performance on various speech recognition tasks. These systems almost utilize the Mel-frequency cepstral coefficients or the Mel-scale log-filterbank coefficients, which are based on short-time Fourier transform. Although...
The authors are developing a talking robot which is a mechanical vocalization system modeling the human articulatory system. The talking robot is constructed with mechanical parts that are made by referring to human vocal organs biologically and functionally. In this study, a newly redesign artificial vocal cord is developed for the purpose of extending the speaking capability of the talking robot...
This paper describes a novel algorithm to improve the performance of sparsity based single-channel speech separation(SCSS) problem based on compressed sensing which is an emerging technique for efficient data reconstruction. The conventional approach assumes the mixing conditions and source signals are stationary. For practical applications of audio source separation, however, we face the challenges...
We present a method for estimating the body orientation of seated people in a smart room by fusing low-resolution range information collected from downward pointed time-of-flight (ToF) sensors with synchronized speaker identification information from microphone recordings. The ToF sensors preserve the privacy of the occupants in that they only return the range to a small set of hit points. We propose...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.