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.
Failing to identify multi-word expression (MWE) may cause serious problems for many Natural Language Processing (NLP) tasks. Previous approaches heavily depend on language specific knowledge and pre-existing natural language processing (NLP) tools. However, many languages (including Chinese language) have less such resources and tools compared to English. An automatically learn effective features...
During the last five years, the amount of users of online social networks has increased exponentially. With the growing of users, social problems also arise. Due to the nature of these platforms, specifically Twitter, users can express their ideas in the way they prefer no matter if it is racist or not. As the Twitter CEO says, one of the most difficult things for them is to detect and ban people...
This paper studies the influence factor on HMM-based Tibetan Lhasa speech synthesis. In order to find the key factor which makes the most contribution to improve the synthesized Tibetan Lhasa speech, we synthesize Tibetan Lhasa speech by different context labeling and different number of training sentences with different speech synthesis unit, respectively. We build two Tibetan Lhasa speech corpora...
Forensic Voice Comparison (FVC) is increasingly using the likelihood ratio (LR) in order to indicate whether the evidence supports the prosecution (same-speaker) or defender (different-speakers) hypotheses. Nevertheless, the LR accepts some practical limitations due both to its estimation process itself and to a lack of knowledge about the reliability of this (practical) estimation process. It is...
The motivation behind the research on overlapping speech has always been dominated by the need to model human-machine interaction for dialog systems and conversation analysis. To have more complex insights of the interlocutors' intentions behind the interaction, we need to understand the type of overlaps. Overlapping speech signals the interlocutor's intention to grab the floor. This act could be...
We propose a new concept for adapting CNN-based acoustic models using spatial diffuseness features as auxiliary information about the acoustic environment: the spatial diffuseness features are simultaneously employed as acoustic-model input features and to estimate environmental cues for context adaptation, where one convolutional layer is factorized into several sub-layers to represent different...
In this paper, we target improving the accuracy of acoustic modelling for statistical parametric speech synthesis (SPSS) and introduce the convolutional neural network (CNN) due to its powerful capacity in locality modelling. A novel model architecture combining unidirectional long short-term memory (LSTM) and a time-domain convolutional output layer (COL) is proposed and employed to acoustic modelling...
This paper proposes an alternative multi-level approach to duration prediction for improving prosody generation in statistical parametric speech synthesis using multiple Gaussian process experts. We use two duration models at different levels, specifically, syllable and phone. First, we individually train syllable- and phone-level duration models. Then, the predictive distributions of syllable and...
As part of an ongoing research into extracting mission-critical information from Search and Rescue speech communications, a corpus of unscripted, goal-oriented, two-party spoken conversations has been designed and collected. The Sheffield Search and Rescue (SSAR) corpus comprises about 12 hours of data from 96 conversations by 24 native speakers of British English with a southern accent. Each conversation...
Supervised speech separation algorithms seldom utilize output patterns. This study proposes a novel recurrent deep stacking approach for time-frequency masking based speech separation, where the output context is explicitly employed to improve the accuracy of mask estimation. The key idea is to incorporate the estimated masks of several previous frames as additional inputs to better estimate the mask...
Human-robot teams can incorporate advanced technology such as distributed mobile sensor networks, integrated communications, visualization technology, and other means to acquire and assess information. These factors can greatly affect mission effectiveness, safety, and survivability, by providing critical information and suggesting courses of action. However, information overload can result. Tactical...
Behavioral annotation using signal processing and machine learning is highly dependent on training data and manual annotations of behavioral labels. Previous studies have shown that speech information encodes significant behavioral information and be used in a variety of automated behavior recognition tasks. However, extracting behavior information from speech is still a difficult task due to the...
In post disaster situation, the existing network infrastructure might be partly or fully damaged. In that case, a very popular online social network like twitter can be an effective tool, where people can share their views and knowledge about what is actually happening in the affected areas. It is a very challenging task to analyze the situation during the golden hours of any large scale disaster...
A set of lexical categories, analogous to part-of-speech categories for English prose, is defined for source-code identifiers. The lexical category for an identifier is determined from its declaration in the source code, syntactic meaning in the programming language, and static program analysis. Current techniques for assigning lexical categories to identifiers use natural-language part-of-speech...
We looked up to elements present in speech articulation to introduce the proactive haptic articulation as a novel approach for intercommunication. The ability to use a haptic interface as a tool for implicit communication can supplement communication and support near and remote collaborative tasks in virtual and physical environments. In addition, the proactive articulation can be applied during the...
Speech Synthesis System converts written text to speech. To build a natural sounding speech synthesis system, it is essential that the text processing component produce an appropriate sequence of units. Syllable preserves co-articulation effects within the sound unit. In our current work, concatenative method is use to develop a synthesis system using syllable as the basic unit which includes Jodhakshars,...
This paper presents a phonetic analysis of Arabic speech language phonemes using hidden Markov model classifiers and their confusion matrices. For this purpose, a new classical Arabic speech corpus was planned and designed. The corpus is based on recitations from The Holy Quran of specific scripts. Semi-manual labeling and segmentation of the audio files along with other language resources such as...
I-vector space feature has been recently proved to be very efficient in speaker recognition field. In this paper, we assess using the i-vector approach for emotional speaker recognition in order to boost the performance which is deteriorated by emotions. The key idea of the i-vector algorithm is to represent each speaker by a fixed length and low dimensional feature vector. The concatenation of these...
Sound source separation at low-latency requires that each incoming frame of audio data be processed at very low delay, and outputted as soon as possible. For practical purposes involving human listeners, a 20 ms algorithmic delay is the uppermost limit which is comfortable to the listener. In this paper, we propose a low-latency (algorithmic delay < 20 ms) deep neural network (DNN) based source...
Automatic and spontaneous speech emotion recognition is an important part of a human-computer interactive system. However, emotion identification in spontaneous speech is difficult because most often the emotion expressed by the speaker are not necessarily as prominent as in acted speech. In this paper, we propose a spontaneous speech emotion recognition framework that makes use of the associated...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.