Sciweavers

INTERSPEECH
2010
13 years 6 months ago
The use of subvector quantization and discrete densities for fast GMM computation for speaker verification
Last year, we showed that the computation of a GMM-UBMbased speaker verification (SV) system may be sped up by 30 times by using a high-density discrete model (HDDM) on the NIST 2...
Guoli Ye, Brian Mak
INTERSPEECH
2010
13 years 6 months ago
Continuous speech recognition with a TF-IDF acoustic model
Information retrieval methods are frequently used for indexing and retrieving spoken documents, and more recently have been proposed for voice-search amongst a pre-defined set of ...
Geoffrey Zweig, Patrick Nguyen, Jasha Droppo, Alex...
INTERSPEECH
2010
13 years 6 months ago
Detecting categorical perception in continuous discrimination data
We present a method for assessing categorical perception from continuous discrimination data. Until recently, categorical perception of speech has exclusively been measured by dis...
Paul Boersma, Katerina Chládková
INTERSPEECH
2010
13 years 6 months ago
Phonetic realization of second occurrence focus in Japanese
Previous studies have recently agreed that second occurrence focus is phonetically realized as prosodic prominence. What has been missing in the previous studies, however, is a co...
Satoshi Nambu, Yong-cheol Lee
INTERSPEECH
2010
13 years 6 months ago
Speaking style dependency of formant targets
Previous work on formant targets has assumed that these targets are independent of the speaking style. In this paper, we estimate consonant and vowel targets in a database of &quo...
Akiko Amano-Kusumoto, John-Paul Hosom, Alexander K...
INTERSPEECH
2010
13 years 6 months ago
Phonetic subspace mixture model for speaker diarization
This paper presents an improved distance measure for speaker clustering in speaker diarization systems. The proposed phonetic subspace mixture (PSM) model introduces phonetic info...
I-Fan Chen, Shih-Sian Cheng, Hsin-Min Wang
INTERSPEECH
2010
13 years 6 months ago
An HMM trajectory tiling (HTT) approach to high quality TTS
We propose an HMM Trajectory Tiling (HTT) approach to high quality TTS, which is our entry to Blizzard Challenge 2010. In HTT, first refined HMM is trained with the Minimum Genera...
Yao Qian, Zhi-Jie Yan, Yijian Wu, Frank K. Soong, ...
INTERSPEECH
2010
13 years 6 months ago
Laryngealization and features for Chinese tonal recognition
It is well known that the lowest tone in Mandarin, a language without contrastive phonation, often co-occurs with laryngealization/creaky voice quality, and we provide evidence th...
Kristine M. Yu
INTERSPEECH
2010
13 years 6 months ago
A comparative large scale study of MLP features for Mandarin ASR
MLP based front-ends have shown significant complementary properties to conventional spectral features. As part of the DARPA GALE program, different MLP features were developed fo...
Fabio Valente, Mathew Magimai-Doss, Christian Plah...
INTERSPEECH
2010
13 years 6 months ago
What do you mean, you're uncertain?: the interpretation of cue words and rising intonation in dialogue
This paper investigates how rising intonation affects the interpretation of cue words in dialogue. Both cue words and rising intonation express a range of speaker attitudes like u...
Catherine Lai