Sciweavers

INTERSPEECH
2010
12 years 11 months ago
Direct construction of compact context-dependency transducers from data
This paper describes a new method for building compact context-dependency transducers for finite-state transducer-based ASR decoders. Instead of the conventional phonetic decision...
David Rybach, Michael Riley
INTERSPEECH
2010
12 years 11 months ago
VAD-measure-embedded decoder with online model adaptation
We previously proposed a decoding method for automatic speech recognition utilizing hypothesis scores weighted by voice activity detection (VAD)-measures. This method uses two Gau...
Tasuku Oonishi, Koji Iwano, Sadaoki Furui
INTERSPEECH
2010
12 years 11 months ago
A factorial sparse coder model for single channel source separation
We propose a probabilistic factorial sparse coder model for single channel source separation in the magnitude spectrogram domain. The mixture spectrogram is assumed to be the sum ...
Robert Peharz, Michael Stark, Franz Pernkopf, Yann...
INTERSPEECH
2010
12 years 11 months ago
Text normalization based on statistical machine translation and internet user support
In this paper, we describe and compare systems for text normalization based on statistical machine translation (SMT) methods which are constructed with the support of internet use...
Tim Schlippe, Chenfei Zhu, Jan Gebhardt, Tanja Sch...
INTERSPEECH
2010
12 years 11 months ago
Influence of lexical tones on intonation in kammu
The aim of this study is to investigate how the presence of lexical tones influences the realization of focal accent and sentence intonation. The language studied is Kammu, a lang...
Anastasia Karlsson, David House, Jan-Olof Svantess...
INTERSPEECH
2010
12 years 11 months ago
On using voice source measures in automatic gender classification of children's speech
Acoustic characteristics of speech signals differ with gender due to physiological differences of the glottis and the vocal tract. Previous research [1] showed that adding the voi...
Gang Chen, Xue Feng, Yen-Liang Shue, Abeer Alwan
INTERSPEECH
2010
12 years 11 months ago
Impact of lack of acoustic feedback in EMG-based silent speech recognition
This paper presents our recent advances in speech recognition based on surface electromyography (EMG). This technology allows for Silent Speech Interfaces since EMG captures the e...
Matthias Janke, Michael Wand, Tanja Schultz
INTERSPEECH
2010
12 years 11 months ago
The role of higher-level linguistic features in HMM-based speech synthesis
We analyse the contribution of higher-level elements of the linguistic specification of a data-driven speech synthesiser to the naturalness of the synthetic speech which it genera...
Oliver Watts, Junichi Yamagishi, Simon King
INTERSPEECH
2010
12 years 11 months ago
Invariant integration features combined with speaker-adaptation methods
Speaker-normalization and -adaptation methods are essential components of state-of-the-art speech recognition systems nowadays. Recently, so-called invariant integration features ...
Florian Müller, Alfred Mertins