We present the first English syllabification system to improve the accuracy of letter-tophoneme conversion. We propose a novel discriminative approach to automatic syllabification...
This paper presents a new approach to language model construction, learning a language model not from text, but directly from continuous speech. A phoneme lattice is created using...
Graham Neubig, Masato Mimura, Shinsuke Mori, Tatsu...
Features generated by Non-Negative Matrix Factorization (NMF) have successfully been introduced into robust speech processing, including noise-robust speech recognition and detect...
Wavelet analysis has found widespread use in signal processing and many classification tasks. Nevertheless, its use in dynamic pattern recognition have been much more restricted ...
This paper presents an algorithm to optimize the tradeoff between rate and expected end-to-end distortion of a video sequence transmitted over a packet network. The approach optim...
Enrico Masala, Hua Yang, Kenneth Rose, Juan Carlos...