Sciweavers

ICASSP
2009
IEEE
14 years 2 months ago
Improving multi-lattice alignment based spoken keyword spotting
In previous work, we showed that using a lattice instead of the 1-best path to represent both the query and the utterance being searched is beneficial for spoken keyword spotting...
Hui Lin, Alex Stupakov, Jeff Bilmes
ICASSP
2009
IEEE
14 years 2 months ago
Experimenting with a global decision tree for state clustering in automatic speech recognition systems
In modern automatic speech recognition systems, it is standard practice to cluster several logical hidden Markov model states into one physical, clustered state. Typically, the cl...
Jasha Droppo, Alex Acero
ICASSP
2009
IEEE
14 years 2 months ago
Emotion recognition from speech: Putting ASR in the loop
This paper investigates the automatic recognition of emotion from spoken words by vector space modeling vs. string kernels which have not been investigated in this respect, yet. A...
Björn Schuller, Anton Batliner, Stefan Steidl...
ICASSP
2009
IEEE
14 years 2 months ago
Ranging energy optimization for robust sensor positioning
We address ranging energy optimization for an unsynchronized localization system, which features robust sensor positioning, in the sense that specific accuracy requirements are f...
Tao Wang, Geert Leus, Dries Neirynck, Feng Shu, Li...
ICASSP
2009
IEEE
14 years 2 months ago
Independent component analysis for noisy speech recognition
Independent component analysis (ICA) is not only popular for blind source separation but also for unsupervised learning when the observations can be decomposed into some independe...
Hsin-Lung Hsieh, Jen-Tzung Chien, Koichi Shinoda, ...
ICASSP
2009
IEEE
14 years 2 months ago
Exploiting T-junctions for depth segregation in single images
Occlusion is one of the major consequences of the physical image generation process: it occurs when an opaque object partly obscures the view of another object further away from t...
Mariella Dimiccoli, Philippe Salembier
ICASSP
2009
IEEE
14 years 2 months ago
LSH banding for large-scale retrieval with memory and recall constraints
Locality Sensitive Hashing (LSH) is widely used for efficient retrieval of candidate matches in very large audio, video, and image systems. However, extremely large reference dat...
Michele Covell, Shumeet Baluja
ICASSP
2009
IEEE
14 years 2 months ago
Accelerated 3D MRI of vocal tract shaping using compressed sensing and parallel imaging
3D MRI of the upper airway has provided valuable insights into vocal tract shaping and data for the modeling of speech production. Small movements of articulators can lead to larg...
Yoon-Chul Kim, Shrikanth S. Narayanan, Krishna S. ...
ICASSP
2009
IEEE
14 years 2 months ago
An analytical approach to sound field reproduction with a movable sweet spot using circular distributions of loudspeakers
Sound field reproduction methods like higher order Ambisonics which are based on orthogonal expansions always introduce a limitation of the spatial bandwidth of the secondary sou...
Jens Ahrens, Sascha Spors