| 1 |
Replicating in Naxi (Tibeto-Burman) an experiment designed for Yorùbá: An approach to ‘prominence-sensitive prosody' vs. ‘calculated prosody'
|
|
|
|
In: Proceedings of Speech Prosody 2006, Dresden ; https://hal.archives-ouvertes.fr/hal-00130341 ; 2006, pp.819-822 (2006)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Pitch and Voice Quality Characteristics of the Lexical Word-Tones of Tamang, as Compared with Level Tones (Naxi data) and Pitch-plus-Voice-Quality Tones (Vietnamese data)
|
|
|
|
In: Proceedings of Speech Prosody 2006, Dresden ; https://hal.archives-ouvertes.fr/hal-00134939 ; 2006, pp. 819-822 (2006)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Replicating in Naxi (Tibeto-Burman) an experiment designed for Yorùbá: An approach to ‘prominence-sensitive prosody' vs. ‘calculated prosody'
|
|
|
|
In: Proceedings of Speech Prosody 2006, Dresden ; https://hal.archives-ouvertes.fr/hal-00130341 ; 2006, pp.819-822 (2006)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Pitch and Voice Quality Characteristics of the Lexical Word-Tones of Tamang, as Compared with Level Tones (Naxi data) and Pitch-plus-Voice-Quality Tones (Vietnamese data)
|
|
|
|
In: Proceedings of Speech Prosody 2006, Dresden ; https://hal.archives-ouvertes.fr/hal-00134939 ; 2006, pp. 819-822 (2006)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Evaluation of a multilingual TTS system with respect to the prosodic quality
|
|
|
|
In: http://141.64.226.10/~mixdorff/thesis/files/hoffmann_mixdorff.pdf (1999)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Multilevel rhythm control for speech synthesis using hybrid data driven and rulebased approaches
|
|
|
|
In: http://www1.hft-leipzig.de/jokisch/publications/jokisch-hirschfeld-icslp1998-rhythm.pdf (1998)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Measuring the Quality of Pronunciation Dictionaries
|
|
|
|
In: http://www.clsp.jhu.edu/pmla2002/cd/papers/wolff.pdf
|
|
BASE
|
|
Show details
|
|
|
| 8 |
ISCA Archive Automatic Learning and Optimization of Pronunciation Dictionaries 1
|
|
|
|
In: http://isca-speech.org/archive_open/archive_papers/adaptation/adap_159.pdf
|
|
BASE
|
|
Show details
|
|
|
| 9 |
ISCA Archive Measuring the Quality of Pronunciation Dictionaries
|
|
|
|
In: http://isca-speech.org/archive_open/archive_papers/pmla/pmla_117.pdf
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Audiovisual Tools for Phonetic and Articulatory Visualization in Computer-Aided Pronunciation Training
|
|
|
|
In: http://www.se.cuhk.edu.hk/hccl/publications/pub/LNCS5967.pdf
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Acoustic Analysis of Postvocalic /l / in Chinese Learners of German in the Context of an Overall Perception Experiment
|
|
|
|
In: http://project.cgm.unive.it/events/SLaTE2011/papers/Jokisch-ding-hoffmann-SLaTE2011-revised.pdf
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Perception and Production of Mandarin Tones by German Speakers
|
|
|
|
In: http://speechprosody2010.illinois.edu/papers/100153.pdf
|
|
BASE
|
|
Show details
|
|
|
| 13 |
Spectral distance costs for multilingual unit selection in speech synthesis
|
|
|
|
In: http://www.eurasip.org/Proceedings/Ext/SPECOM2006/papers/047.pdf
|
|
BASE
|
|
Show details
|
|
|
| 14 |
ISCA Archive CREATING AN INDIVIDUAL SPEECH RHYTHM: A DATA DRIVEN APPROACH
|
|
|
|
In: http://isca-speech.org/archive_open/archive_papers/ssw3/ssw3_115.pdf
|
|
BASE
|
|
Show details
|
|
|
| 15 |
PROSODIC MODELING OF SYNTHESISED GERMAN WORDS
|
|
|
|
In: http://www.icphs2007.de/conference/Papers/1265/1265.pdf
|
|
BASE
|
|
Show details
|
|
|
| 16 |
Measuring Pitch with Historic Phonetic Devices
|
|
|
|
In: http://www.isca-speech.org/archive/sp2006/papers/sp06_139.pdf
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Bayes Optimal Classification for Corpus-Based Unit Selection in TTS Synthesis
|
|
|
|
In: http://jth2008.ehu.es/cd/pdfs/articulo/art_35.pdf
|
|
BASE
|
|
Show details
|
|
|
| 18 |
Resynthesis of Prosodic Information Using the Cepstrum Vocoder
|
|
|
|
In: http://speechprosody2010.illinois.edu/papers/100358.pdf
|
|
Abstract:
The naturalness of synthetic speech depends on automatic extraction of prosodic features and prosody modeling. To improve the naturalness of the synthesized speech, we want to apply the concept of Analysis-by-Synthesis of prosodic information. Therefore, the accents and phrases of the speech signal were extracted using the quantitative Fujisaki model in a recognition model. In a generative model we resynthesized the speech signal using a cepstrum vocoder. The excitation signal of the vocoder are the pitch marks (PM), which were calculated from multiple levels of the accent and phrase marking algorithm. A preference test was performed to confirm the performance of the proposed method. For every speech signal four signals were resynthesized according to the calculated PM. Evaluators compared the resynthesized signals with one another. Results show that the quality of the resynthesized signal after prosodic marking is better. Index Terms: analysis-by-synthesis, prosodic marking, Fujisaki model
|
|
URL: http://speechprosody2010.illinois.edu/papers/100358.pdf
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.302.6203
|
|
BASE
|
|
Hide details
|
|
|
| 19 |
ISCA Archive An Interactive Course on Speech Synthesis
|
|
|
|
In: http://isca-speech.org/archive_open/archive_papers/matisse/mati_061.pdf
|
|
BASE
|
|
Show details
|
|
|
|
|
