SSW8 Accepted Papers

Program

SSW8 Accepted Papers

  • Oral presentations: 20min + 5min for questions
  • Poster presentations: 100min; landscape format (max. height: 95 cm ; max. width: 194cm)

    Saturday, August 31st

    Oral Session O1

    Automatic detection of inhalation breath pauses for improved pause modelling in HMM-TTSNorbert Braunschweiler and Langzhou Chen.
    Role of Pausing in Text-to-Speech Synthesis for Simultaneous InterpretationVivek Kumar Rangarajan Sridhar, John Chen, Srinivas Bangalore and Alistair Conkie.
    Minimum Error Rate Training for Phrasing in Speech SynthesisAlok Parlikar and Alan Black.
    HMM-based Speech Synthesis of Live Sports Commentaries: Integration of a Two-Layer Prosody AnnotationBenjamin Picart, Sandrine Brognaux and Thomas Drugman.

    Poster Session P1

    Parametric model for vocal effort interpolation with Harmonics Plus Noise ModelsÀngel Calzada Defez, Joan Claudi Socoró Carrié and Robert Clark.
    Vietnamese HMM-based Speech Synthesis with prosody informationAnh-Tuan Dinh, Thanh-Son Phan, Tat-Thang Vu and Chi-Mai Luong.
    Context labels based on "bunsetsu" for HMM-based speech synthesis of JapaneseHiroya Hashimoto, Keikichi Hirose and Nobuaki Minematsu.
    Using Adaptation to Improve Speech Transcription Alignment in Noisy and Reverberant EnvironmentsYoshitaka Mamiya, Adriana Stan, Junichi Yamagishi, Peter Bell, Oliver Watts, Robert Clark and Simon King.
    Speech synthesis using a maximally decimated pseudo QMF bank for embedded devicesNobuyuki Nishizawa and Tsuneo Kato.
    HMM-based sCost quality control for unit selection speech synthesisSathish Pammi and Marcela Charfuelan.
    Understanding Factors in Emotion PerceptionLakshmi Saheer and Blaise Potard.
    Multilingual Number Transcription for Text-to-Speech ConversionRubén San-Segundo, Juan Manuel Montero, Mircea Giurgiu, Ioana Muresan and Simon King.
    Noise-Robust Voice Conversion Based on Spectral Mapping on Sparse SpaceRyoichi Takashima, Ryo Aihara, Tetsuya Takiguchi and Yasuo Ariki.
    Cross-variety speaker transformation in HSMM-based speech synthesisMarkus Toman, Michael Pucher and Dietmar Schabus.

    Oral Session O2

    Residual Compensation based on Articulatory Feature-based Phone Clustering for Hybrid Mandarin Speech SynthesisYi-Chin Huang, Chung-Hsien Wu and Shih-Lun Lin.
    Investigation of intra-speaker spectral parameter variation and its prediction towards improvement of spectral conversion metricTatsuo Inukai, Tomoki Toda, Graham Neubig, Sakriani Sakti and Satoshi Nakamura.
    Text to Speech in New Languages without a Standardized OrthographySunayana Sitaram, Gopala Anumanchipalli, Justin Chiu, Alok Parlikar and Alan Black.
    Unsupervised and lightly-supervised learning for rapid construction of TTS systems in multiple languages from ‘found’ data: evaluation and analysisOliver Watts, Adriana Stan, Rob Clark, Yoshitaka Mamiya, Mircea Giurgiu, Junichi Yamagishi and Simon King.

    Sunday, September 1st

    Oral Session O3

    A phonetic-contrast motivated adaptation to control the degree-of-articulation on Italian HMM-based synthetic voicesMauro Nicolao, Fabio Tesser and Roger K. Moore.
    Using neighbourhood density and selective SNR boosting to increase the intelligibility of synthetic speech in noiseCassia Valentini-Botinhao, Mirjam Wester, Junichi Yamagishi and Simon King.
    Noise Robustness in HMM-TTS Speaker AdaptationKayoko Yanagisawa, Javier Latorre, Vincent Wan, Mark J. F. Gales and Simon King.

    Oral Session O4

    New Method for Rapid Vocal Tract Length Adaptation in HMM-based Speech SynthesisDaniel Erro, Agustin Alonso, Luis Serrano, Eva Navas and Inma Hernaez.
    Text-to-speech synthesizer based on combination of composite wavelet and hidden Markov modelsNobukatsu Hojo, Kota Yoshizato, Hirokazu Kameoka, Daisuke Saito and Shigeki Sagayama.
    An experimental comparison of multiple vocoder typesQiong Hu, Korin Richmond, Junichi Yamagishi and Javier Latorre.
    Statistical Model Training Technique for Speech Synthesis Based on Speaker ClassYusuke Ijima, Noboru Miyazaki and Hideyuki Mizuno.

    Poster Session P2

    Is Intelligibility Still the Main Problem? A Review of Perceptual Quality Dimensions of Synthetic SpeechFlorian Hinterleitner, Christoph Norrenbrock and Sebastian Möller.
    Evaluation of contextual descriptors for HMM-based speech synthesis in FrenchSébastien Le Maguer, Nelly Barbot and Olivier Boeffard.
    Towards Speaking Style Transplantation in Speech SynthesisJaime Lorenzo-Trueba, Roberto Barra-Chicote, Junichi Yamagishi, Oliver Watts and Juan M. Montero.
    Investigating the shortcomings of HMM synthesisThomas Merritt and Simon King.
    Prosodic analysis of storytelling discourse modes and narrative situations oriented to Text-to-Speech synthesisRaúl Montaño, Francesc Alías and Josep Ferrer.
    Objective evaluation measures for speaker-adaptive HMM-TTS systemsUlpu Remes, Reima Karhila and Mikko Kurimo.
    Experiments with Signal-Driven Symbolic Prosody for Statistical Parametric Speech SynthesisFabio Tesser, Giacomo Sommavilla, Giulio Paci and Piero Cosi.
    Significance of word-terminal syllables for prediction of phrase breaks in Text-to-Speech systems for Indian languagesAnandaswarup Vadapalli, Peri Bhaskararao and Kishore Prahallad.
    The Effect of Age and Native Speaker Status on Synthetic Speech IntelligibilityCatherine Watson, Wei Liu and Bruce MacDonald.
    Exemplar-based Voice Conversion using Non-negative Spectrogram DeconvolutionZhizheng Wu, Tuomas Virtanen, Tomi Kinnunen, Eng Siong Chng and Haizhou Li.

    Monday, September 2nd

    Oral Session O5

    Mage - Reactive articulatory feature control of HMM-based parametric speech synthesisMaria Astrinaki, Alexis Moinet, Junichi Yamagishi, Korin Richmond, Zhen-Hua Ling, Simon King and Thierry Dutoit.
    Systematic database creation for expressive singing voice synthesis controlMarti Umbert, Jordi Bonada and Merlijn Blaauw.

    Oral Session O6

    Expressive Speech Synthesis: Synthesising AmbiguityMatthew Aylett, Blaise Potard and Christopher Pidcock.
    Interactional Adequacy as a Factor in the Perception of Synthesized SpeechTimo Baumann and David Schlangen.
    A novel irregular voice model for HMM-based speech synthesisTamás Gábor Csapó and Géza Németh.
    Expression of Speaker's Intentions through Sentence-Final Particle/Intonation Combinations in Japanese Conversational Speech SynthesisKazuhiko Iwata and Tetsunori Kobayashi.

    Demo Session

    Poster Session P3

    SASSC: A Standard Arabic Single Speaker CorpusIbrahim Almosallam, Atheer Alkhalifa, Mansour Alghamdi, Mohamed Alkanhal and Ashraf Alkhairy.
    Prosodically Modifying Speech for Unit Selection Speech Synthesis DatabasesLadan Golipour, Alistair Conkie and Ann Syrdal.
    Combining a Vector Space Representation of Linguistic Context with a Deep Neural Network for Text-To-Speech SynthesisHeng Lu, Simon King and Oliver Watts.
    Is Unit Selection Aware of Audible Artifacts?Jindřich Matoušek, Daniel Tihelka and Milan Legát.
    Development of Electrolarynx with Hands-Free Prosody ControlKenji Matsui, Kenta Kimura, Yoshihisa Nakatoh and Yumiko O. Kato.
    A Hybrid TTS between Unit Selection and HMM-based TTS under limited data conditionsTrung-Nghia Phung, Chi Mai Luong and Masato Akagi.
    Wavelets for intonation modeling in HMM speech synthesisAntti Suni, Daniel Aalto, Tuomo Raitio, Paavo Alku and Martti Vainio.
    Multi-variety adaptive acoustic modeling in HSMM-based speech synthesisMarkus Toman, Michael Pucher and Dietmar Schabus.
    A Common Attribute based Unified HTS framework for Speech Synthesis in Indian LanguagesRamani B, S Lilly Christina, G Anushiya Rachel, Sherlin Solomi V, Mahesh Kumar Nandwana, Anusha Prakash, Aswin Shanmugam S, Raghava Krishnan, S Kishore Prahalad, K Samudravijaya, P Vijayalakshmi, T Nagarajan and Hema Murthy.
    Cross-lingual speaker adaptation based on factor analysis using bilingual speech data for HMM-based speech synthesisTakenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku and Keiichi Tokuda.
ISCA

International Speech Communication Association.

SynSIG

The aim of SynSIG is to promote the study of Speech Synthesis in general. Its international and multi-disciplinary nature provides a means for sharing information both to and from different research communities involved in the synthesis of various languages.

UPC

BarcelonaTech is close to the people who make up the university community, to future students, to researchers, to entrepreneurs, to institutions and to companies.