In unit selection based concatenative speech systems, join cost, which measures how well two units can be joined together, is one of the main criteria for selecting appropriate units from the inventory. The ideal join cost will measure perceived discontinuity, based on easily measurable spectral properties of the units being joined, in order to ensure smooth and natural-sounding synthetic speec...

Model compensation techniques for noise-robust speech recognition approximate the corrupted speech distribution. is work introduces a sampling method that, given speech and noise distributions and a mismatch function, in the limit calculates the corrupted speech likelihood exactly. For this, it transforms the integral in the likelihood expression, and then applies sequential importance resampli...

A hybrid connectionist-HMM speech recognizer uses a neural network acoustic classifier. This network estimates the posterior probability that the acoustic feature vectors at the current time step should be labelled as each of around 50 phone classes. We sought to exploit informal observations of the distinctions in this posterior domain between nonspeech audio and speech segments well-modeled b...

A hybrid connectionist-HMM speech recognizer uses a neural network acoustic classifier. This network estimates the posterior probability that the acoustic feature vectors at the current time step should be labelled as each of around 50 phone classes. We sought to exploit informal observations of the distinctions in this posterior domain between nonspeech audio and speech segments well-modeled b...

In this paper, a computational goal for a monaural speech separation system is proposed. Since this goal is derived by maximizing the signal-to-noise ratio (SNR), it is called the optimal ratio mask (ORM). Under the approximate W-Disjoint Orthogonality assumption which almost always holds due to the sparse nature of speech, theoretical analysis shows that the ORM can improve the SNR about 10log...

network measurements (e.g., loss rates and delays), and little attention has been paid to the quality perceived by end-users of the applications running over the network. Here, we address the issue of integrating speech quality subjective scores and network parameters measurements, for designing control algorithms that would yield the best QoS that could be delivered under a given communication...

In this paper, we propose a novel method to detect robot-directed speech by situated understanding in human-robot physical interaction. The originality of this work is the introduction of a Multimodal Semantic Confidence measure based domain classification method, which is used to decide whether the speech can be interpreted as a feasible action under the current physical situation in an object...