Sciweavers

INTERSPEECH
2010
12 years 11 months ago
Feature versus model based noise robustness
Over the years, the focus in noise robust speech recognition has shifted from noise robust features to model based techniques such as parallel model combination and uncertainty de...
Kris Demuynck, Xueru Zhang, Dirk Van Compernolle, ...
INTERSPEECH
2010
12 years 11 months ago
Identifying articulatory goals from kinematic data using principal differential analysis
Articulatory goals can be highly indicative of lexical intentions, but are rarely used in speech classification tasks. In this paper we show that principal differential analysis c...
Michael Reimer, Frank Rudzicz
INTERSPEECH
2010
12 years 11 months ago
Convexity and fast speech extraction by split bregman method
A fast speech extraction (FSE) method is presented using convex optimization made possible by pause detection of the speech sources. Sparse unmixing filters are sought by l1 regul...
Meng Yu, Wenye Ma, Jack Xin, Stanley Osher
INTERSPEECH
2010
12 years 11 months ago
On speaker adaptive training of artificial neural networks
In the paper we present two techniques improving the recognition accuracy of multilayer perceptron neural networks (MLP ANN) by means of adopting Speaker Adaptive Training. The us...
Jan Trmal, Jan Zelinka, Ludek Müller
INTERSPEECH
2010
12 years 11 months ago
Full body aero-tactile integration in speech perception
We follow up on our research demonstrating that aerotactile information can enhance or interfere with accurate auditory perception, even among uninformed and untrained perceivers ...
Donald Derrick, Bryan Gick
INTERSPEECH
2010
12 years 11 months ago
Study on interaction between entropy pruning and kneser-ney smoothing
The paper presents an in-depth analysis of a less known interaction between Kneser-Ney smoothing and entropy pruning that leads to severe degradation in language model performance...
Ciprian Chelba, Thorsten Brants, Will Neveitt, Pen...
INTERSPEECH
2010
12 years 11 months ago
The relevance of timing, pauses and overlaps in dialogues: detecting topic changes in scenario based meetings
We present an investigation of the relevance of simple conversational features as indicators of topic shifts in small-group meetings. Three proposals for representation of dialogu...
Saturnino Luz, Jing Su
INTERSPEECH
2010
12 years 11 months ago
SCARF: a segmental conditional random field toolkit for speech recognition
This paper describes a new toolkit - SCARF - for doing speech recognition with segmental conditional random fields. It is designed to allow for the integration of numerous, possib...
Geoffrey Zweig, Patrick Nguyen
INTERSPEECH
2010
12 years 11 months ago
Multi-pitch estimation by a joint 2-d representation of pitch and pitch dynamics
Multi-pitch estimation of co-channel speech is especially challenging when the underlying pitch tracks are close in pitch value (e.g., when pitch tracks cross). Building on our pr...
Tianyu T. Wang, Thomas F. Quatieri
INTERSPEECH
2010
12 years 11 months ago
Native and non-native speaker judgements on the quality of synthesized speech
The difference between native speakers' and non-native speakers' naturalness judgements of synthetic speech is investigated. Similar/difference judgements are analysed v...
Anna C. Janska, Robert A. J. Clark