SPS Feed

The saliency detection technologies are very useful to analyze and extract important information from given multimedia data, and have already been extensively used in many multimedia applications. Past studies have revealed that utilizing the global cues is effective in saliency detection. Nevertheless, most of prior works mainly considered the single-scale segmentation when the global cues are employed. In this paper, we attempt to incorporate the multi-scale global cues for saliency detection problem. 

Predicting articulatory movements from audio or text has diverse applications, such as speech visualization. Various approaches have been proposed to solve the acoustic-articulatory mapping problem. However, their precision is not high enough with only acoustic features available. Recently, deep neural network (DNN) has brought tremendous success in various fields, like speech recognition and image processing.

The procedure for extracting a cryptographic key from noisy sources, such as biometrics and physically uncloneable functions (PUFs), is known as fuzzy extractor (FE). Although FE constructions deal with discrete sources, most noisy sources are continuous. In the continuous case, it is required to transform the source to a discrete one. 

In this paper, the achievable secrecy rate of a relay-assisted massive multiple-input multiple-output (MIMO) downlink is investigated in the presence of a multi-antenna active/passive eavesdropper. The excess degrees-of-freedom offered by a massive MIMO base-station (BS) are exploited for sending artificial noise (AN) via random and null-space precoders.

The importance of normalizing biometric features or matching scores is understood in the multimodal biometric case, but there is less attention to the unimodal case. Prior reports assess the effectiveness of normalization directly on biometric performance. We propose that this process is logically comprised of two independent steps: (1) methods to equalize the effect of each biometric feature on the similarity scores calculated from all the features together...

Nonlinear acoustic echo cancellation (AEC) is a highly challenging task in a single-microphone; hence, the AEC technique with a microphone array has also been considered to more effectively reduce the residual echo. However, these algorithms track only a linear acoustic path between the loudspeaker and the microphone array. 

Lexical-based metrics such as BLEU, NIST, and WER have been widely used in machine translation (MT) evaluation. However, these metrics badly represent semantic relationships and impose strict identity matching, leading to moderate correlation with human judgments. In this paper, we propose a novel MT automatic evaluation metric Semantic Travel Distance (STD) based on word embeddings. STD incorporates both semantic and lexical features (word embeddings and n -gram and word order) into one metric.

Dialogue policy plays an important role in task-oriented spoken dialogue systems. It determines how to respond to users. The recently proposed deep reinforcement learning (DRL) approaches have been used for policy optimization. However, these deep models are still challenging for two reasons: first, many DRL-based policies are not sample efficient; and second, most models do not have the capability of policy transfer between different domains.