Sciweavers

Share
CVPR
2012
IEEE
6 years 6 months ago
Enhanced continuous sign language recognition using PCA and neural network features
In this work a Gaussian Hidden Markov Model (GHMM) based automatic sign language recognition system is built on the SIGNUM database. The system is trained on appearance-based feat...
Yannick L. Gweth, Christian Plahl, Hermann Ney
IUI
2012
ACM
6 years 12 months ago
Mobile texting: can post-ASR correction solve the issues? an experimental study on gain vs. costs
The next big step in embedded, mobile speech recognition will be to allow completely free input as it is needed for messaging like SMS or email. However, unconstrained dictation r...
Michael Feld, Saeedeh Momtazi, Farina Freigang, Di...
ICASSP
2011
IEEE
7 years 7 months ago
Joint encoding of the waveform and speech recognition features using a transform codec
We propose a new transform speech codec that jointly encodes a wideband waveform and its corresponding wideband and narrowband speech recognition features. For distributed speech ...
Xing Fan, Michael L. Seltzer, Jasha Droppo, Henriq...
ICASSP
2011
IEEE
7 years 8 months ago
Why word error rate is not a good metric for speech recognizer training for the speech translation task?
Speech translation (ST) is an enabling technology for cross-lingual oral communication. A ST system consists of two major components: an automatic speech recognizer (ASR) and a ma...
Xiaodong He, Li Deng, Alex Acero
ICASSP
2011
IEEE
7 years 8 months ago
cROVER: Improving ROVER using automatic error detection
Recognizer Output Voting Error Reduction (ROVER), is a well-known procedure for decoders’ combination aiming at reducing the Word Error Rate (WER) in transcription applications....
Kacem Abida, Fakhri Karray, Wafa Abida
ICASSP
2011
IEEE
7 years 8 months ago
Using morpheme and syllable based sub-words for polish LVCSR
Polish is a synthetic language with a high morpheme-perword ratio. It makes use of a high degree of inflection leading to high out-of-vocabulary (OOV) rates, and high Language Mo...
M. Ali Basha Shaik, Amr El-Desoky Mousa, Ralf Schl...
ICASSP
2011
IEEE
7 years 8 months ago
Progress in example based automatic speech recognition
In this paper we present a number of improvements that were recently made to the template based speech recognition system developed at ESAT. Combining these improvements resulted ...
Kris Demuynck, Dino Seppi, Hugo Van hamme, Dirk Va...
INTERSPEECH
2010
7 years 11 months ago
Data pruning for template-based automatic speech recognition
In this paper we describe and analyze a data pruning method in combination with template-based automatic speech recognition. We demonstrate the positive effects of polishing the t...
Dino Seppi, Dirk Van Compernolle
ACL
2009
8 years 2 months ago
Improving Automatic Speech Recognition for Lectures through Transformation-based Rules Learned from Minimal Data
We demonstrate that transformation-based learning can be used to correct noisy speech recognition transcripts in the lecture domain with an average word error rate reduction of 12...
Cosmin Munteanu, Gerald Penn, Xiaodan Zhu
NAACL
2010
8 years 2 months ago
A Hybrid Morphologically Decomposed Factored Language Models for Arabic LVCSR
In this work, we try a hybrid methodology for language modeling where both morphological decomposition and factored language modeling (FLM) are exploited to deal with the complex ...
Amr El-Desoky, Ralf Schlüter, Hermann Ney
books