Smiling Virtual Characters Corpora

To create smiling virtual characters, the different morphological and dynamic characteristics of the virtual characters smiles and the impact of the virtual characters smiling behavior on the users need to be identified. For this purpose, we have collected two corpora: one directly created by users and the other resulting from the interaction between virtual characters and users. We present in details these two corpora in the article.

Speaker Recognition In Noisy Conditions With Limited Training Data

In this paper we present a novel method for performing speaker recognition with very limited training data and in the presence of background noise. Similarity-based speaker recognition is considered so that speaker models can be created with limited training speech data. The proposed similarity is a form of cosine similarity used as a distance measure between speech feature vectors. Each speech frame is modelled using subband features, and into this framework, multicondition training and optimal feature selection are introduced, making the system capable of performing speaker recognition in the presence of realistic, time-varying noise, which is unknown during training. Speaker identi?cation experiments were carried out using the SPIDRE database. The performance of the proposed new system for noise compensation is compared to that of an oracle model; the speaker identi?cation accuracy for clean speech by the new system trained with limited training data is compared to that of a GMM trained with several minutes of speech. Both comparisons have demonstrated the effectiveness of the new model. Finally, experiments were carried out to test the new model for speaker identi?cation given limited training data and with differing levels and types of realistic background noise. The results have demonstrated the robustness of the new system.

Robust Audio-Visual Speech Recognition under Noisy Audio-Video Conditions

This paper presents the maximum weighted stream posterior (MWSP) model as a robust and efficient stream integration method for audio-visual speech recognition in environments, where the audio or video streams may be subjected to unknown and time-varying corruption. A significant advantage of MWSP is that it does not require any specific measurements of the signal in either stream to calculate appropriate stream weights during recognition, and as such it is modality-independent. This also means that MWSP complements and can be used alongside many of the other approaches that have been proposed in the literature for this problem. For evaluation we used the large XM2VTS database for speaker-independent audio-visual speech recognition. The extensive tests include both clean and corrupted utterances with corruption added in either/both the video and audio streams using a variety of types (e.g., MPEG-4 video compression) and levels of noise. The experiments show that this approach gives excellent performance in comparison to another well-known dynamic stream weighting approach and also compared to any fixed-weighted integration approach in both clean conditions or when noise is added to either stream. Furthermore, our experiments show that the MWSP approach dynamically selects suitable integration weights on a frame-by-frame basis according to the level of noise in the streams and also according to the naturally fluctuating relative reliability of the modalities even in clean conditions. The MWSP approach is shown to maintain robust recognition performance in all tested conditions, while requiring no prior knowledge about the type or level of noise.

Local versus nonlocal cloning in a noisy environment

We address the distribution of quantum information among many parties in the presence of noise. In particular, we consider how to optimally send to m receivers the information encoded into an unknown coherent state. On one hand, a local strategy is considered, consisting in a local cloning process followed by direct transmission. On the other hand, a telecloning protocol based on nonlocal quantum correlations is analysed. Both the strategies are optimized to minimize the detrimental effects due to losses and thermal noise during the propagation. The comparison between the local and the nonlocal protocol shows that telecloning is more effective than local cloning for a wide range of noise parameters. Our results indicate that nonlocal strategies can be more robust against noise than local ones, thus being suitable candidates for playing a major role in quantum information networks.

Multimode entanglement and telecloning in a noisy environment

We address the generation, propagation, and application of multipartite continuous variable entanglement in a noisy environment. In particular, we focus our attention on the multimode entangled states achievable by second-order nonlinear crystals-i.e., coherent states of the SU(m,1) group-which provide a generalization of the twin-beam state of a bipartite system. The full inseparability in the ideal case is shown, whereas thresholds for separability are given for the tripartite case in the presence of noise. We find that entanglement of tripartite states is robust against thermal noise, both in the generation process and during propagation. We then consider coherent states of SU(m,1) as a resource for multipartite distribution of quantum information and analyze a specific protocol for telecloning, proving its optimality in the case of symmetric cloning of pure Gaussian states. We show that the proposed protocol also provides the first example of a completely asymmetric 1 -> m telecloning and derive explicitly the optimal relation among the different fidelities of the m clones. The effect of noise in the various stages of the protocol is taken into account, and the fidelities of the clones are analytically obtained as a function of the noise parameters. In turn, this permits the optimization of the telecloning protocol, including its adaptive modifications to the noisy environment. In the optimized scheme the clones' fidelity remains maximal even in the presence of losses (in the absence of thermal noise), for propagation times that diverge as the number of modes increases. In the optimization procedure the prominent role played by the location of the entanglement source is analyzed in details. Our results indicate that, when only losses are present, telecloning is a more effective way to distribute quantum information than direct transmission followed by local cloning.

Combining multi-band and frequency-filtering techniques for speech recognition in noisy environments

While current speech recognisers give acceptable performance in carefully controlled environments, their performance degrades rapidly when they are applied in more realistic situations. Generally, the environmental noise may be classified into two classes: the wide-band noise and narrow band noise. While the multi-band model has been shown to be capable of dealing with speech corrupted by narrow-band noise, it is ineffective for wide-band noise. In this paper, we suggest a combination of the frequency-filtering technique with the probabilistic union model in the multi-band approach. The new system has been tested on the TIDIGITS database, corrupted by white noise, noise collected from a railway station, and narrow-band noise, respectively. The results have shown that this approach is capable of dealing with noise of narrow-band or wide-band characteristics, assuming no knowledge about the noisy environment.

Belief change with noisy sensing in the situation calculus

Situation calculus has been applied widely in arti?cial intelligence to model and reason about actions and changes in dynamic systems. Since actions carried out by agents will cause constant changes of the agents’ beliefs, how to manage
these changes is a very important issue. Shapiro et al. [22] is one of the studies that considered this issue. However, in this framework, the problem of noisy sensing, which often presents in real-world applications, is not considered. As a
consequence, noisy sensing actions in this framework will lead to an agent facing inconsistent situation and subsequently the agent cannot proceed further. In this paper, we investigate how noisy sensing actions can be handled in iterated
belief change within the situation calculus formalism. We extend the framework proposed in [22] with the capability of managing noisy sensings. We demonstrate that an agent can still detect the actual situation when the ratio of noisy sensing actions vs. accurate sensing actions is limited. We prove that our framework subsumes the iterated belief change strategy in [22] when all sensing actions are accurate. Furthermore, we prove that our framework can adequately handle belief introspection, mistaken beliefs, belief revision and belief update even with noisy sensing, as done in [22] with accurate sensing actions only.

Fast Mining of Interesting Phrases from Subsets of Text Corpora

We address the problem of mining interesting phrases from subsets of a text corpus where the subset is specified using a set of features such as keywords that form a query. Previous algorithms for the problem have proposed solutions that involve sifting through a phrase dictionary based index or a document-based index where the solution is linear in either the phrase dictionary size or the size of the document subset. We propose the usage of an independence assumption between query keywords given the top correlated phrases, wherein the pre-processing could be reduced to discovering phrases from among the top phrases per each feature in the query. We then outline an indexing mechanism where per-keyword phrase lists are stored either in disk or memory, so that popular aggregation algorithms such as No Random Access and Sort-merge Join may be adapted to do the scoring at real-time to identify the top interesting phrases. Though such an approach is expected to be approximate, we empirically illustrate that very high accuracies (of over 90%) are achieved against the results of exact algorithms. Due to the simplified list-aggregation, we are also able to provide response times that are orders of magnitude better than state-of-the-art algorithms. Interestingly, our disk-based approach outperforms the in-memory baselines by up to hundred times and sometimes more, confirming the superiority of the proposed method.

Coreference resolution for portuguese using parallel corpora word alignment

A área de Extração da Informação tem como objetivo essencial investigar métodos e técnicas para transformar a informação não estruturada presente em textos de língua natural em dados estruturados. Um importante passo deste processo é a resolução de correferência, tarefa que identifica diferentes sintagmas nominais que se referem a mesma entidade no discurso. A área de estudos sobre resolução de correferência tem sido extensivamente pesquisada para a Língua Inglesa (Ng, 2010) lista uma série de estudos da área, entretanto tem recebido menos atenção em outras línguas. Isso se deve ao fato de que a grande maioria das abordagens utilizadas nessas pesquisas são baseadas em aprendizado de máquina e, portanto, requerem uma extensa quantidade de dados anotados.