Sciweavers

INTERSPEECH
2010
13 years 6 days ago
On generating combilex pronunciations via morphological analysis
Combilex is a high quality lexicon that has been developed specifically for speech technology purposes and recently released by CSTR. Combilex benefits from many advanced features...
Korin Richmond, Robert A. J. Clark, Susan Fitt
INTERSPEECH
2010
13 years 6 days ago
Combining many alignments for speech to speech translation
Alignment combination (symmetrization) has been shown to be useful for improving Machine Translation (MT) models. Most existing alignment combination techniques are based on heuri...
Sameer Maskey, Steven J. Rennie, Bowen Zhou
INTERSPEECH
2010
13 years 6 days ago
On-the-fly lattice rescoring for real-time automatic speech recognition
This paper presents a method for rescoring the speech recognition lattices on-the-fly to increase the word accuracy while preserving low latency of a real-time speech recognition ...
Hasim Sak, Murat Saraclar, Tunga Güngör
INTERSPEECH
2010
13 years 6 days ago
Improvements of search error risk minimization in viterbi beam search for speech recognition
This paper describes improvements in a search error risk minimization approach to fast beam search for speech recognition. In our previous work, we proposed this approach to reduc...
Takaaki Hori, Shinji Watanabe, Atsushi Nakamura
INTERSPEECH
2010
13 years 6 days ago
Performance estimation of noisy speech recognition considering recognition task complexity
To ensure a satisfactory QoE (Quality of Experience) and facilitate system design in speech recognition services, it is essential to establish a method that can be used to efficie...
Takeshi Yamada, Tomohiro Nakajima, Nobuhiko Kitawa...
INTERSPEECH
2010
13 years 6 days ago
Probabilistic integration of joint density model and speaker model for voice conversion
This paper describes a novel approach to voice conversion using both a joint density model and a speaker model. In voice conversion studies, approaches based on Gaussian Mixture M...
Daisuke Saito, Shinji Watanabe, Atsushi Nakamura, ...
INTERSPEECH
2010
13 years 6 days ago
Influence of musical training on perception of L2 speech
The current study reports specific cases in which a positive transfer of perceptual ability from the music domain to the language domain occurs. We tested whether musical training...
Makiko Sadakata, Lotte van der Zanden, Kaoru Sekiy...
INTERSPEECH
2010
13 years 6 days ago
Semi-supervised part-of-speech tagging in speech applications
When no training or adaptation data is available, semisupervised training is a good alternative for processing new domains. We perform Bayesian training of a part-of-speech (POS) ...
Richard Dufour, Benoît Favre
INTERSPEECH
2010
13 years 6 days ago
Similarity scoring for recognizing repeated out-of-vocabulary words
We develop a similarity measure to detect repeatedly occurring Out-of-Vocabulary words (OOV), since these carry important information. Sub-word sequences in the recognition output...
Mirko Hannemann, Stefan Kombrink, Martin Karafi&aa...
INTERSPEECH
2010
13 years 6 days ago
HMM-based prosodic structure model using rich linguistic context
This paper presents a study on the use of deep syntactical features to improve prosody modeling 1 . A French linguistic processing chain based on linguistic preprocessing, morphos...
Nicolas Obin, Xavier Rodet, Anne Lacheret