Sorry, you need to enable JavaScript to visit this website.

ICASSP 2021 - IEEE International Conference on Acoustics, Speech and Signal Processing is the world’s largest and most comprehensive technical conference focused on signal processing and its applications. The ICASSP 2021 conference will feature world-class presentations by internationally renowned speakers, cutting-edge session topics and provide a fantastic opportunity to network with like-minded professionals from around the world. Visit website.

Probabilistic context-free grammars (PCFGs) have been proposed to capture password distributions, and further been used in password guessing attacks and password strength meters. However, current PCFGs suffer from the limitation of inaccurate segmentation of password, which leads to misestimation of password probability and thus seriously affects their performance. In this paper, we propose a word extraction approach for passwords, and further present an improved PCFG model, called WordPCFG.


The general approaches for polarity analysis in dialogue, e.g. Multiple Instance Learning (MIL), have achieved significant progress.
However, one significant drawback of current approaches is that the contribution of an utterance towards the polarity being a \emph{black-box}.
For existing methods, the polarity contained in each utterance, which we call meta-polarity, is not explicitly utilized.
In this paper, we study the problem of adding interpretability to the overall polarity by predicting the meta-polarity at the same time.


We consider the problem of identifying the members of a botnet under an application-layer (L7) DDoS attack, where a target site is flooded with a large number of requests that emulate legitimate users’ patterns. This challenging problem has been recently addressed with reference to two simplified scenarios, where either all bots pick requests from the same emulation dictionary (total overlap), or they are divided in separate clusters corresponding to distinct emulation dictionaries (no overlap at all).


A consensus based distributed algorithm to compute
the spectral radius of a network is proposed. The spectral radius
of the graph is the largest eigenvalue of the adjacency matrix, and
is a useful characterization of the network graph. Conventionally,
centralized methods are used to compute the spectral radius, which
involves eigenvalue decomposition of the adjacency matrix of the
underlying graph. Our distributed algorithm uses a simple update
rule to reach consensus on the spectral radius, using only local


Language models (LM) have been widely deployed in modern ASR systems. The LM is often trained by minimizing its perplexity on speech transcript. However, few studies try to discriminate a "gold" reference against inferior hypotheses. In this work, we propose a large margin language model (LMLM). LMLM is a general framework that enforces an LM to assign a higher score to the "gold" reference, and a lower one to the inferior hypothesis. The general framework is applied to three pretrained LM architectures: left-to-right LSTM, transformer encoder, and transformer decoder.


Music source separation is important for applications such as karaoke and remixing. Much of previous research
focuses on estimating magnitude short-time Fourier transform (STFT) and discarding phase information. We observe that,
for singing voice separation, phase has the potential to make considerable improvement in separation quality. This paper
proposes a complex-domain deep learning method for voice and accompaniment separation. The proposed method employs


Phase unwrapping is a classical ill-posed problem which aims to recover the true phase from wrapped phase. In this paper, we introduce a novel Convolutional Neural Network (CNN) that incorporates a Spatial Quad-Directional Long Short Term Memory (SQD-LSTM) for phase unwrapping, by formulating it as a regression problem. Incorporating SQD-LSTM can circumvent the typical CNNs' inherent difficulty of learning global spatial dependencies which are vital when recovering the true phase. Furthermore, we employ a problem specific composite loss function to train this network.