A sonorant detection scheme using Mel-frequency cepstral coefficients and support vector machines (SVMs) is presented and tested in a variety of noise conditions. Adapting the classifier threshold using an estimate of the noise level is used to bias the classifier to effectively compensate for mismatched training and testing conditions. The adaptive threshold classifier achieves low frame error...

We propose a weakly-supervised framework for action labeling in video, where only the order of occurring actions is required during training time. The key challenge is that the per-frame alignments between the input (video) and label (action) sequences are unknown during training. We address this by introducing the Extended Connectionist Temporal Classification (ECTC) framework to efficiently e...

Frame-of-reference training has been shown to be an effective intervention for improving the accuracy of performance ratings (e.g., Woehr & Huffcutt, 1994). Despite evidence in support of the effectiveness of frame-of-reference training, few studies have empirically addressed the ultimate goal of such training, which is to teach raters to share a common conceptualization of performance (Athey &...

In this paper, we propose a neural-based coding scheme in which an artificial neural network is exploited to automatically compress and decompress speech signals by a trainable approach. Having a two-stage training phase, the system can be fully specified to each speech frame and have robust performance across different speakers and wide range of spoken utterances. Indeed, Frame-based nonlinear...

the type of training system and application of calcium spray have considerable effects on storability of fruits. in this study, the effects of calcium chloride spray (0, 0.75, 1.5 and 3 g.l-1) in three times during 2, 4 and 6 weeks before harvest time on apple (malus domestica) fruits cvs. ‘gala’ and ‘delbarestival’, which trained in three different training systems (v shape, hightech and cordo...

This paper considers discriminative training of acoustic models for Mandarin large vocabulary continuous speech recognition. Two frame-level information cues were explored and integrated into the minimum phone error (MPE) training. First, the frame-level entropy of Gaussian posterior probabilities obtained from the word lattice of the training utterance was exploited to weight the framelevel st...

We propose a novel training strategy for Tacotron-based text-to-speech (TTS) system that improves the speech styling at utterance level. One of key challenges in prosody modeling is lack reference makes explicit difficult. The proposed technique doesn’t require annotations from data. It attempt to model explicitly either, but rather encodes association between input text and its styles using TT...

Frame-semantic parsing is a kind of automatic semantic role labeling performed according to the FrameNet paradigm. The paper reports a novel approach for boosting frame-semantic parsing accuracy through the use of the C5.0 decision tree classifier, a commercial version of the popular C4.5 decision tree classifier, and manual rule enhancement. Additionally, the possibility to replace C5.0 by an ...