Notes:
The Blizzard Challenge is an annual competition organized by the Language Technologies Institute of Carnegie Mellon University to evaluate auditory speech synthesis on common datasets. The goal is to take an agreed upon speech dataset and build a synthetic voice using the provided tools, with the resulting synthesized speech being evaluated by speech experts and volunteer listeners. The challenge has been ongoing since 2005, with entries typically consisting of research papers describing the methods and techniques used in creating the synthetic voices. The challenge covers a variety of languages and tasks, including text-to-speech, voice conversion, and speaker adaptation.
Resources:
- Festvox: Blizzard Challenge
- SynSIG Speech Synthesis Special Interest Group
See also:
The Blizzard Challenge 2005: Evaluating corpus-based speech synthesis on common databases A Black, K Tokuda – Proceedings of Interspeech, 2005 – festvox.org In order to better understand different speech synthesis tech- niques on the same data, we have devised a challenge that will help us better compare research techniques in building corpus- based speech synthesizers. The basic challenge is to take the publicly available CMU … Cited by 101 Related articles All 15 versions Cite Save More
Details of the Nitech HMM-based speech synthesis system for the Blizzard Challenge 2005 ZEN Heiga, T Tomoki, M Nakamura… – IEICE transactions on …, 2007 – search.ieice.org In January 2005, an open evaluation of corpus-based text-to-speech synthesis systems using common speech datasets, named< I> Blizzard Challenge 2005, was conducted. Nitech group participated in this challenge, entering an HMM-based speech synthesis … Cited by 141 Related articles All 11 versions Cite Save
An overview of Nitech HMM-based speech synthesis system for Blizzard Challenge 2005 H Zen, T Toda – 2005 – library.naist.jp In the present paper, hidden Markov model (HMM) based speech synthesis system developed in Nagoya Institute of Technology (Nitech-HTS) for a competition of text-to- speech synthesis systems using the same speech databases, named Blizzard Challenge … Cited by 77 Related articles All 10 versions Cite Save
USTC system for Blizzard Challenge 2006 an improved HMM-based speech synthesis method ZH Ling, YJ Wu, YP Wang, L Qin… – Blizzard Challenge …, 2006 – festvox.org ABSTRACT This paper introduces the USTC speech synthesis system for Blizzard Challenge 2006. The HMM-based parametric synthesis approach was adopted for its convenience and effectiveness in building a new voice, especially for the nonnative … Cited by 67 Related articles All 5 versions Cite Save More
Speaker-Independent HMM-based Speech Synthesis System: HTS-2007 System for the Blizzard Challenge 2007 J Yamagishi, H Zen, T Toda, K Tokuda – 2007 – library.naist.jp This paper describes an HMM-based speech synthesis system developed by the HTS working group for the Blizzard Challenge 2007. To further explore the potential of HMM- based speech synthesis, we incorporate new features in our conventional system which … Cited by 48 Related articles All 8 versions Cite Save
The blizzard challenge 2008 V Karaiskosa, S Kingb, RAJ Clarkb, C Mayob – 2008 – cstr.ed.ac.uk Abstract The Blizzard Challenge 2008 was the fourth annual Blizzard Challenge. This year, participants were asked to build two voices from a UK English corpus and one voice from a Mandarin Chinese corpus. This is the first time that a language other than English has … Cited by 53 Related articles All 5 versions Cite Save More
Statistical analysis of the Blizzard Challenge 2007 listening test results RAJ Clark, M Podsiadlo, M Fraser, C Mayo… – Proc. Blizzard Challenge …, 2007 – festvox.org Abstract Blizzard 2007 is the third Blizzard Challenge, in which participants build voices from a common dataset. A large listening test is conducted which allows comparison of systems in terms of naturalness and intelligibility. New sections were added to the listening test for … Cited by 45 Related articles All 7 versions Cite Save
The Nitech-NAIST HMM-based speech synthesis system for the Blizzard Challenge 2006 ZEN Heiga, T Tomoki, K Tokuda – IEICE transactions on …, 2008 – search.ieice.org We describe a statistical parametric speech synthesis system developed by a joint group from the Nagoya Institute of Technology (Nitech) and the Nara Institute of Science and Technology (NAIST) for the annual open evaluation of text-to-speech synthesis systems … Cited by 55 Related articles All 15 versions Cite Save
The blizzard challenge 2007 M Fraser, S King – Proc. BLZ3-2007 (in Proc. SSW6), 2007 – festvox.org Abstract In Blizzard 2007, the third Blizzard Challenge, participants were asked to build voices from a dataset, a defined subset and, following certain constraints, a subset of their choice. A set of test sentences was then released to be synthesised. An online evaluation … Cited by 46 Related articles All 3 versions Cite Save
Large scale evaluation of corpus-based synthesizers: results and lessons from the blizzard challenge 2005. CL Bennett – INTERSPEECH, 2005 – cs.cmu.edu Abstract The Blizzard Challenge 2005 was a large scale international evaluation of various corpus-based speech synthesis systems using common datasets. Six sites from around the world, both academic and industrial, participated in this evaluation, the first ever to … Cited by 43 Related articles All 8 versions Cite Save More
The HTS-2008 system: Yet another evaluation of the speaker-adaptive HMM-based speech synthesis system in the 2008 Blizzard Challenge J Yamagishi, H Zen, YJ Wu, T Toda, K Tokuda – 2008 – library.naist.jp For the 2008 Blizzard Challenge, we used the same speakeradaptive approach to HMM- based speech synthesis that was used in the HTS entry to the 2007 challenge, but an improved system was built in which the multi-accented English average voice model was … Cited by 39 Related articles All 12 versions Cite Save
The USTC and iFlytek speech synthesis systems for Blizzard Challenge 2007 ZH Ling, L Qin, H Lu, Y Gao, LR Dai, RH Wang… – Blizzard Challenge …, 2007 – festvox.org Abstract This paper introduces the speech synthesis systems developed by USTC and iFlytek for Blizzard Challenge 2007. These two systems are both HMM-based ones and employ similar training algorithms, where contextual dependent HMMs for spectrum, F0 … Cited by 41 Related articles All 3 versions Cite Save
The Blizzard Challenge 2008 S King, RAJ Clark, C Mayo, V Karaiskos – 2008 – era.lib.ed.ac.uk The Blizzard Challenge 2008 was the fourth annual Blizzard Challenge. This year, participants were asked to build two voices from a UK English corpus and one voice from a Man-darin Chinese corpus. This is the first time that a language other than English has … Cited by 51 Related articles All 8 versions Cite Save
The blizzard challenge 2006 CL Bennett, AW Black – Proc. Blizzard Challenge, 2006 – cs.cmu.edu Abstract Last year the Blizzard Challenge 2005 introduced the speech synthesis community to the concept of large scale, multi-site evaluation of TTS systems using common data. In this, the second year of the Blizzard Challenge, we again tackled this task. Participation … Cited by 31 Related articles All 9 versions Cite Save More
Multilingual MARY TTS participation in the Blizzard Challenge 2009 M Schröder, S Pammi, O Türk – Proc. Blizzard Challenge, 2009 – festvox.org Abstract The paper describes the Blizzard Challenge 2009 participation of MARY TTS, an open-source TTS system using a unit selection voice. We briefly outline the new language support framework we provide so that people can add support for their languages to … Cited by 20 Related articles All 6 versions Cite Save More
The GlottHMM speech synthesis entry for Blizzard Challenge 2010 A Suni, T Raitio, M Vainio, P Alku – The Blizzard Challenge 2010 …, 2010 – users.tkk.fi • Finnish speech synthesis has been studied in the University of Helsinki with a special emphasis on speech prosody• Research on speech processing and acoustics has a long history in Aalto University (formerly known as Helsinki University of Technology, TKK)• … Cited by 17 Related articles All 6 versions Cite Save More
The UPC TTS system description for the 2008 blizzard challenge A Bonafonte, A Moreno, J Adell, PD Agüero… – … the Blizzard Challenge, …, 2008 – Citeseer Abstract This paper presents the UPC TTS system named Ogmios. It was used to generate the voices in UK English and Mandarin Chinese for Blizzard Challenge 2008. Ogmios is a system based on unit-selection using acoustic and phonetic features both in target and … Cited by 16 Related articles All 11 versions Cite Save More
The MARY TTS entry in the Blizzard Challenge 2008 M Schröder, M Charfuelan, S Pammi, O Türk – Proc. Blizzard Challenge, 2008 – Citeseer Abstract The present paper reports on the DFKI entry to the Blizzard challenge 2008. The main difference of our system compared to last year is a new join model inspired by last year’s iFlytek paper; the effect seems small, but measurable in the sense that it leads to … Cited by 16 Related articles All 5 versions Cite Save More
The CSTR/EMIME HTS System for Blizzard Challenge 2010 J Yamagishi, O Watts – 2010 – era.lib.ed.ac.uk In the 2010 Blizzard Challenge, we focused on improving steps relating to feature extraction and labeling in the procedures for training HMM-based speech synthesis systems. New auditory scales were used for spectral features and F0 representation. We have also … Cited by 24 Related articles All 4 versions Cite Save
Festival multisyn voices for the 2007 blizzard challenge. K Richmond, V Strom, RAJ Clark, J Yamagishi, S Fitt – 2007 – era.lib.ed.ac.uk This paper describes selected aspects of the Festival Multisyn entry to the Blizzard Challenge 2007. We provide an overview of the process of building the three required voices from the speech data provided. This paper focuses on new features of Multisyn … Cited by 16 Related articles All 8 versions Cite Save
Multisyn voices from ARCTIC data for the Blizzard challenge. RAJ Clark, K Richmond, S King – 2005 – era.lib.ed.ac.uk This paper describes the process of building unit selection voices for the Festival Multisyn engine using four ARCTIC datasets, as part of the Blizzard evaluation challenge. The build process is almost entirely automatic, with very little need for human intervention. We … Cited by 15 Related articles All 8 versions Cite Save
The IBM submission to the 2006 Blizzard text-to-speech challenge E Eide, R Fernandez, R Hoory, W Hamza, Z Kons… – … Challenge, 2006 – festvox.org Abstract In this paper, we present two concatenative text-to-speech systems built from the “Blizzard Challenge” speech databases. The two systems differ primarily in their segment selection cost function. One system has our baseline cost function, and the other has a … Cited by 3 Related articles All 2 versions Cite Save More
The VUB Blizzard Challenge 2010 Entry: Towards Automatic Voice Building L Latacz, W Mattheyses, W Verhelst – Blizzard Challenge, 2010 – etro.vub.ac.be Abstract In this paper we describe the voices we submitted to the 2010 Blizzard Challenge, a yearly challenge to evaluate auditory speech synthesis on common data. One of the goals of a datadriven synthesizer, such as ours, is to generalize the speech database in such a … Cited by 2 Related articles All 4 versions Cite Save More
Multisyn voice for the Blizzard Challenge 2006 R Clark, K Richmond, V Strom, S King – Proc. Blizzard Challenge …, 2006 – cstr.ed.ac.uk Abstract This paper describes the process of building unit selection voices for the Festival Multisyn engine using the ATR dataset provided for the Blizzard Challenge 2006. We begin by discussing recent improvements that we have made to the Multisyn voice building … Cited by 11 Related articles All 5 versions Cite Save More
Mary tts participation in the Blizzard Challenge 2007 M Schröder, A Hunecke – Proceedings of the Blizzard Challenge 2007, 2007 – dfki.de Abstract This paper describes the second participation of the open source MARY TTS unit selection system in a Blizzard challenge. Compared to last year’s system, a number of welldefined changes have been made to the algorithm, concerning unit definition, prosody … Cited by 12 Related articles All 6 versions Cite Save More
The blizzard challenge 2005 CMU entry-a method for improving speech synthesis systems. J Kominek, CL Bennett, B Langner, AR Toth – INTERSPEECH, 2005 – cs.cmu.edu Abstract In CMU’s Blizzard Challenge 2005 entry we investigated twelve ideas for improving Festival-based unit selection voices. We tracked progress by adopting a 3-tiered strategy in which candidate ideas must pass through three stages of listening tests to warrant … Cited by 11 Related articles All 11 versions Cite Save More
Improving instrumental quality prediction performance for the Blizzard Challenge TH Falk, S Möller, V Karaiskos, S King – Proc. Blizzard Challenge Text-to- …, 2008 – festvox.org Abstract—In this paper, the performance of the standard in-strumental quality prediction algorithm ITU-T P. 563 is reported based on the 2007 and 2008 Blizzard Challenge speech data. The algorithm, which is optimized for natural speech, is shown to obtain poor … Cited by 9 Related articles All 6 versions Cite Save More
Performance evaluation of the speaker-independent HMM-based speech synthesis system “HTS 2007” for the Blizzard Challenge 2007 J Yamagishi, T Nose, H Zen, T Toda… – Acoustics, Speech and …, 2008 – ieeexplore.ieee.org Abstract This paper describes a speaker-independent/adaptive HMM-based speech synthesis system developed for the Blizzard Challenge 2007. The new system, named” HTS- 2007″, employs speaker adaptation (CSMAPLR+ MAP), feature-space adaptive training, … Cited by 8 Related articles All 9 versions Cite Save
The ustc system for blizzard challenge 2009 H Lu, ZH Ling, M Lei, CC Wang, HH Zhao… – Blizzard Challenge …, 2009 – festvox.org Abstract This paper introduces the USTC’s speech synthesis system for Blizzard Challenge 2009. USTC attended all English tasks including the hub tasks and the spoke tasks. According to the various conditions for different tasks, different versions of HMM based … Cited by 8 Related articles All 3 versions Cite Save More
An HMM trajectory tiling (HTT) approach to high quality TTS Microsoft entry to Blizzard Challenge 2010 Y Qian, Z Yan, Y Wu, FK Soong, G Zhang, L Wang – 2010 – Citeseer Abstract 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 Generation Error (MGE) criterion; then trajectory generated by the refined HMM is to guide … Cited by 8 Related articles Cite Save More
Evaluating Ivona speech synthesis system for Blizzard Challenge 2006 M Kaszczuk, L Osowski – Blizzard Workshop, Pittsburgh, 2006 – festvox.org Abstract In this paper we wish to describe special version of Ivona Speech Synthesis System with US English voice developed in IVO Software for The Blizzard Challenge 2006. An evaluation made by Speech Experts group, which gave the highest note to Ivona shows … Cited by 6 Related articles Cite Save More
The ustc system for blizzard challenge 2010 Y Jiang, ZH Ling, M Lei, CC Wang, L Heng… – Blizzard Challenge …, 2010 – Citeseer Abstract This paper introduces the speech synthesis system developed by USTC for Blizzard Challenge 2010. USTC attended all English tasks including the hub tasks and the spoke tasks. According to the various conditions for different tasks, different versions of synthesis … Cited by 6 Related articles All 2 versions Cite Save More
On building a concatenative speech synthesis system from the blizzard challenge speech databases. W Hamza, R Bakis, Z Shuang, H Zen – INTERSPEECH, 2005 – festvox.org Abstract In this paper, we compare two methods of building a concatenative speech synthesis system from the relatively small,“Blizzard Challenge” speech databases. In the first method we build a system directly from the Blizzard databases using the IBM … Cited by 5 Related articles All 2 versions Cite Save
The AHOLAB Blizzard Challenge 2009 Entry I Sainz, D Erro, E Navas, I Hernáez… – … . Blizzard Challenge …, 2009 – festvox.org Abstract This paper describes the process of building unit selection voices for our participation in the Blizzard Challenge 2009. Out of the three voices required (EH1: 15 hours UK English, EH2: 1 hour UK English subset and MH: 6000-utterance Mandarin Chinese) … Cited by 5 Related articles All 4 versions Cite Save More
The IVO Software Blizzard Challenge 2009 Entry: Improving IVONA Text-To-Speech M Kaszczuk, L Osowski – Blizzard Challenge Workshop, Edinburgh, …, 2009 – Citeseer Abstract This paper describes a special version of IVONA Text-To-Speech for a GB English voice designed and developed by IVO Software for The Blizzard Challenge 2009. The architecture of this system is based on an improved IVONA Text-To-Speech originally … Cited by 7 Related articles All 3 versions Cite Save More
The GlottHMM entry for Blizzard Challenge 2011: Utilizing source unit selection in HMM-based speech synthesis for improved excitation generation A Suni, T Raitio, M Vainio, P Alku – The Blizzard Challenge 2011 …, 2011 – festvox.org Abstract This paper describes the GlottHMM speech synthesis system for Blizzard Challenge 2011. GlottHMM is a hidden Markov model (HMM) based speech synthesis system that utilizes glottal inverse filtering for separating the vocal tract and the glottal source from … Cited by 6 Related articles All 2 versions Cite Save More
An overview of the VUB entry for the 2008 blizzard challenge L Latacz, Y Kong, W Mattheyses, W Verhelst – … Blizzard Challenge, 2008 – Citeseer Abstract In this paper, we describe the configuration of our synthesizer, as used for the Blizzard Challenge the first time. Two new UK English voices were built for the DSSP synthesizer, our in-house unit selection synthesizer, which uses non-uniform units and a … Cited by 4 Related articles All 6 versions Cite Save More
The Blizzard Challenge 2013 S King, AW Black, K Tokuda, K Prahallad – 2013 – synsig.org In order to better understand and compare research techniques in building corpus-based speech synthesizers on the same data, the annual Blizzard Challenges 2005–2012 were held. We are now pleased to call for participation in the ninth challenge: Blizzard … Cited by 12 Related articles All 4 versions Cite Save More
The Blizzard Challenge 2009 AW Black, S King, K Tokuda – 2009 – synsig.org The 2009 Challenge will be similar to the 2008 Challenge, but with a new “hub and spoke” design, allowing participants to opt in or out of some parts of the Challenge. The “hub” task, required from all participants, is to take the released speech data, build synthetic voices, … Cited by 5 Related articles All 6 versions Cite Save More
The Blizzard Challenge 2006 CMU entry introducing hybrid trajectory-selection synthesis J Kominek, A Black – Blizzard Challenge Workshop, 2006 – festvox.org Abstract Acknowledging the lessons of Blizzard Challenge 2005–that smooth prosodic cadence supersedes spectral resolution–but wanting a system devoid of vocoding artifacts– we introduce a hybrid trajectory-selection synthesizer. Using a parametric synthesizer to … Cited by 3 Related articles All 6 versions Cite Save More
I2R Text-to-Speech System for Blizzard Challenge 2009 M Dong, L Cen, P Chan, DY Huang, D Zhu… – Blizzard Challenge …, 2009 – Citeseer Abstract This paper describes I2R’s submission to the Blizzard Challenge 2010 speech synthesis evaluation. This is our third participation in the challenge. In this paper, we will describe our main approaches to building the required voices. We will introduce the … Cited by 3 Related articles All 4 versions Cite Save More
The Toshiba entry for the 2007 Blizzard Challenge S Buchholz, N Braunschweiler… – … . Blizzard Challenge …, 2007 – toshiba-europe.com Abstract This paper describes the system with which we took part in the Blizzard Challenge for the first time. It describes how we created our own annotation from scratch and introduces the various system components, in particular the back-end. Results show that our system … Cited by 3 Related articles All 7 versions Cite Save
Glottal source and prosodic prominence modelling in HMM-based speech synthesis for the Blizzard Challenge 2009 JS Andersson, JP Cabral, L Badino, J Yamagishi… – 2009 – era.lib.ed.ac.uk This paper describes the CSTR entry for the Blizzard Challenge 2009. The work focused on modifying two parts of the Nitech 2005 HTS speech synthesis system to improve naturalness and contextual appropriateness. The first part incorporated an implementation of the … Cited by 3 Related articles All 10 versions Cite Save
Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2009 K Oura, YJ Wu, K Tokuda – University of Edinburgh, 2009 – festvox.org Abstract This paper describes a hidden Markov model (HMM)-based speech synthesis system developed for the Blizzard Challenge 2010. This system employs STRAIGHT vocoding, minimum generation error (MGE) training, minimum generation error linear … Cited by 3 Related articles All 6 versions Cite Save More
The Jess Blizzard Challenge 2006 Entry P Cahill, J Carson-Berndsen – Blizzard Challenge 2006 Workshop, …, 2006 – muster.ucd.ie Abstract This paper describes the version of the Jess system that participated in the Blizzard Challenge 2006. The Jess system consists of a suite of software tools for processing text and speech. The largest component of the system is a multi-platform unit selection speech … Cited by 2 Related articles All 5 versions Cite Save More
Ucd blizzard challenge 2011 entry P Cahill, U Ogbureke, J Cabral, E Szekely… – … of Blizzard Challenge …, 2011 – festvox.org Abstract This paper gives an overview of the UCD Blizzard Challenge 2011 entry. The entry is a unit selection synthesiser that uses hidden Markov models for prosodic modelling. The evaluation consisted of synthesising 2213 sentences from a high quality 15 hour dataset … Cited by 2 Related articles Cite Save More
Developing a Test Bed of English Text-to-Speech System XIMERA for the Blizzard Challenge 2006 for the Blizzard Challenge 2006 T Toda, H Kawai, T Hirai, J Ni, N Nishizawa… – 2006 – library.naist.jp ” This paper describes the development of a test bed English Text-to-Speech (TTS) system XIMERA at ATR for Blizzard Challenge 2006. The original XIMERA is aimed at constructing very highquality Japanese TTS. Therefore, several modules are customized for our huge- … Cited by 2 Related articles All 8 versions Cite Save
The GlottHMM entry for Blizzard Challenge 2012–Hybrid approach A Suni, T Raitio, M Vainio, P Alku – The Blizzard Challenge 2012 …, 2012 – festvox.org Abstract This paper describes the GlottHMM speech synthesis system for Blizzard Challenge 2012. The aim of the GlottHMM system is to combine high-quality vocoding and detailed prosody modeling in order to produce expressive, high quality, synthetic speech. … Cited by 9 Related articles All 4 versions Cite Save More
Building probabilistic corpus-based speech synthesis systems from the blizzard challenge 2006 speech databases S Sakai – Academic Center for Computing and Media Studies, …, 2006 – Citeseer Abstract In this paper, we describe the development of probabilistic corpus-based concatenative speech synthesis systems with the Blizzard Challenge 2006 speech databases. In the current probabilistic approach, unit selection is directed by probabilistic … Cited by 2 Related articles All 3 versions Cite Save More
The NICT/ATR speech synthesis system for the Blizzard Challenge 2008 R Maia, J Ni, S Sakai, T Toda, K Tokuda, T Shimizu… – 2008 – library.naist.jp This paper describes the development of the NICT/ATR speech synthesizer for the Blizzard Challenge 2008 and discuss the official results. The submitted system is based on the hidden Markov model speech synthesis technology and utilizes an improved excitation … Cited by 2 Related articles All 8 versions Cite Save
Statistical speech synthesis for the blizzard challenge 2008 P Scholtz, A Visagie, J Du Preez – Proc. Blizzard Challenge, 2008 – festvox.org Abstract In this paper we present the details of our first entry for the Blizzard Challenge 2008 speech synthesis evaluation. Our system is a new HMM-based text-to-speech voice building system for the HTS runtime synthesis engine. We entered two UK English voices, one built … Cited by 2 Related articles All 3 versions Cite Save More
The USTC System for Blizzard Challenge 2013 LH Chen, ZH Ling, Y Jiang, Y Song, XJ Xia, YQ Zu… – 2011 – festvox.org Abstract This paper introduces the speech synthesis system developed by USTC for Blizzard Challenge 2013. There are two evaluation tasks in this year: the English audiobook tasks and the pilot tasks on 4 Indian languages. According to the various amount of training data … Cited by 2 Cite Save More
The IBM submission to the 2008 text-to-speech blizzard challenge R Fernandez, Z Kons, S Shechtman, ZW Shuang… – Proc. Blizzard …, 2008 – Citeseer Abstract The 2008 Blizzard speech synthesis challenge provided participants with an opportunity to evaluate their systems in UK English and Mandarin. This paper describes the work behind three IBM systems submitted to the challenge for these two languages. The … Cited by 2 Related articles All 4 versions Cite Save More
The Lessac Technologies System for Blizzard Challenge 2010 R Nitisaroj, R Wilhelms-Tricarico, B Mottershead… – System, 2010 – festvox.org Abstract For Blizzard Challenge 2010, Lessac Technologies built its first British English voice from the provided full database. To enhance methods for target cost calculation and unit selection, instead of traditional phonetic symbols, we used a more finegrained set of … Cited by 2 Related articles All 2 versions Cite Save More
Non-uniform unit selection through search strategy for Blizzard Challenge 2007 F Ding, J Alhonen – Proc. Blizzard Workshop (in proc. SSW6), 2007 – festvox.org Abstract This present paper describes a non-uniform unit selection synthesis system for the Blizzard Challenge 2007. Nonuniform unit is used to maximize the length of unit sequence to be selected for the target sequence. In a minor modification from the previous … Cited by 1 Related articles All 3 versions Cite Save
CircumReality functionality delta: Blizzard Challenge 2007 to 2008 M Rozak – The Blizzard Challenge 2008 – Citeseer Abstract Although performing poorly in the Blizzard Challenge 2008, the CircumReality text- to-speech engine improved significantly from the Blizzard 2007 test. The engine’s acoustic model, prosody model, and acoustic synthesis were improved between tests. This paper … Cited by 1 Related articles All 2 versions Cite Save More
The Toshiba Mandarin TTS System for the Blizzard Challenge 2008 J Li, D Xu, L Yi, X Lou, J Luan, X Wang, L He, J Hao – Challenge, 2008 – festvox.org Abstract This paper introduces the Toshiba Mandarin Text-to-Speech (TTS) system submitted to the Mandarin benchmark of the Blizzard Challenge 2009. The basic framework keeps unchanged with the system in 2008 and we modify the system in several aspects: … Cited by 1 Related articles All 4 versions Cite Save More
BUCEADOR hybrid TTS for blizzard challenge 2011 I Sainz, D Erro, E Navas, J Adell, A Bonafonte Cávez – 2012 – upcommons.upc.edu This paper describes the Text-to-Speech (TTS) systems presented by the Buceador Consortium in the Blizzard Challenge 2011 evaluation campaign. The main system is a concatenative hybrid one that tries to combine the strong points of both statistical and unit … Cited by 3 Related articles All 5 versions Cite Save
The Lessac Technologies system for Blizzard Challenge 2011 R Wilhelms-Tricarico, B Mottershead… – Blizzard Challenge …, 2011 – festvox.org Abstract Lessac Technologies has developed a technology for concatenative speech synthesis based on a novel approach for describing speech in which expressivity, voice quality, and speaking style are fundamental. The main aspect of our system is that instead … Cited by 1 Related articles Cite Save More
The NICT entry for the Blizzard Challenge 2009: an enhanced HMM-based speech synthesis system with trajectory training considering global variance and state- … R Maia, T Toda, S Sakai, Y Shiga, J Ni, H Kawai… – 2009 – library.naist.jp This paper describes the NICT speech synthesis system submitted to the Blizzard Challenge 2009: a hidden Markov model (HMM)-based synthesizer constructed by training trajectory HMMs considering global variance. To improve naturalness of the synthesized speech a … Cited by 1 Related articles All 7 versions Cite Save
Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2011 K Hashimoto, S Takaki, K Oura, K Tokuda – Proc. Blizzard Workshop, 2011 – festvox.org Abstract This paper describes a hidden Markov model (HMM) based speech synthesis system developed for the Blizzard Challenge 2011. In the Blizzard Challenge 2011, we focused on the training algorithm for HMM-based speech synthesis systems. To alleviate … Cited by 2 Related articles All 2 versions Cite Save More
The VoiceText Text-to-Speech System for the Blizzard Challenge WS Jun, DS Na, SW Kim, M Kim, JW Lee, JS Lee – festvox.org Abstract This paper introduces the VoiceText text-to-speech system developed by Voiceware. By means of corpus based concatenative speech synthesis technique, we built high quality synthetic voices using the dataset provided for the Blizzard challenge 2007. … Related articles All 3 versions Cite Save
The Blizzard Challenge: Evaluating Corpus-based Speech Synthesis Techniques AW Black – isca-speech.org ABSTRACT The Blizzard Challenge was started in 2005 as a way to evaluate different corpus speech synthesis techniques on a common data set. It has been noted that it is very hard to evaluate different speech synthesis techniques when different size and quality … Cite Save
MARY TTS HMM-based voices for the Blizzard Challenge 2012 M Charfuelan – festvox.org Abstract This paper describes the first participation of MARY TTS HMM-based voices in a Blizzard challenge. An architecture for synthesis of expressive speech based on the MARY TTS system and sentiment analysis of text is proposed. The creation of several HMM- … Related articles All 4 versions Cite Save More
The NTUT Blizzard Challenge 2009 Entry YF Liao, ML Wu – researchgate.net Abstract This paper describes the process of building HMM-based speech synthesis system (HTS) voices for our participation in the Blizzard Challenge 2009. Out of the two languages required (English and Mandarin Chinese) we only built three Mandarin Chinese voices for … Cited by 1 Related articles All 5 versions Cite Save More
The USTC System for Blizzard Challenge 2012 ZH Ling, XJ Xia, Y Song, CY Yang, LH Chen, LR Dai – staff.ustc.edu.cn Abstract This paper introduces the speech synthesis system developed by USTC for Blizzard Challenge 2012. An audiobook speech corpus is adopted as the training data for system construction this year. Similar to our previous systems, the hidden Markov model (HMM) … Cited by 3 Related articles All 2 versions Cite Save More
The DRESS Blizzard Challenge 2008 Entry HG Rosales, O Jokisch, R Hoffmann – Citeseer Abstract This paper presents the version of the DRESS System that participated in the Blizzard Challenge 2008. Here we show a basic overview of the DRESS system, methodology and a description of its unit selection. We present a novel concept to … Related articles All 2 versions Cite Save More
Towards Perceptual Quality Modeling of Synthesized Audiobooks–Blizzard Challenge 2012 CR Norrenbrock, F Hinterleitner, U Heute, S Möller – festvox.org Abstract This paper reports on recent advances in the field of instrumental quality evaluation of text-to-speech (TTS) synthesis. In particular, a wide range of acoustic quality markers are analyzed concerning their quality-describing power using the audiobook data from the … Related articles Cite Save More
NICT Blizzard Challenge 2010 Entry Y Shiga, T Toda, S Sakai, H Kawai, K Tokuda… – 2010 – library.naist.jp This paper details a speech synthesis system developed at NICT for the Blizzard Challenge 2010. The system depends on an HMM-based speech synthesis technique that possesses two distinctive features: HMM training under global-variance constraint on the parameter … Related articles All 8 versions Cite Save
The ILSP/INNOETICS Text-to-Speech System for the Blizzard Challenge 2013 A Chalamandaris, P Tsiakoulis, S Karabetsos, S Raptis – festvox.org Abstract This paper describes ILSP and INNOETICS Speech Synthesis System entry for the Blizzard Challenge 2013. A description of the underlying system and techniques used is provided, as well as information about the voice building process and discussion on the … Cite Save More
I 2 R Text-to-Speech System for Blizzard Challenge 2011 M Dong, SW Lee, P Chan, L Cen – festvox.org Abstract This paper describes I2R? s submission to the Blizzard Challenge 2011 speech synthesis evaluation. This is our fourth participation in the challenge. In this paper, we will describe our main approaches to building the required voices. We will describe our … Related articles Cite Save More
The WISTON Text-to-Speech System for Blizzard Challenge 2009 J Tao, S Pan, Y Li, Z Wen, Y Wang – Citeseer Abstract The paper introduces the speech synthesis system developed by Institute of Automation, Chinese Academy of Sciences (CASIA) for Blizzard Challenge 2010. The large corpus based speech synthesis system, WISTON, was built to synthesize Mandarin … Related articles All 3 versions Cite Save More
The NTUT Blizzard Challenge 2012 Entry YF Liao, CC Lin, JY Pan – festvox.org Abstract This paper describes our HMM-based speech synthesis system (HTS)[1] submitted to Blizzard Challenge 2012 [2]. This is our first English TTS and also our first audiobook application. In this system, not only linguistic but also semantic features beyond sentence … Related articles Cite Save More
The Simple4All entry to the Blizzard Challenge 2013 O Watts, A Stan, Y Mamiya, A Suni, JM Burgos… – cstr.ed.ac.uk Abstract We describe the synthetic voices entered into the 2013 Blizzard Challenge by the SIMPLE4ALL consortium. The 2013 Blizzard Challenge presents an opportunity to test and benchmark some of the tools we have been developing to address two problems of … Cite Save More
The Lessac Technologies Hybrid Concatenated System for Blizzard Challenge 2012 R Wilhelms-Tricarico, B Mottershead, J Reichenbach… – festvox.org Abstract Lessac Technologies has developed a technology for concatenated speech synthesis based on a novel approach for describing speech in which expressivity, voice quality, and speaking style are fundamental. The main aspect of our system is that instead … Related articles Cite Save More
PUB Entry in the Blizzard Challenge 2011 M Cotescu – Citeseer Abstract The paper presents the entry in this year’s Blizzard Challenge of the Politehnica University of Bucharest. We present a parametric speech synthesis system based on HTS, which tried to achieve two important goals: gain better control over the vocal tract filter, … Related articles All 3 versions Cite Save More
Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2012 S Takaki, K Sawada, K Hashimoto, K Oura, K Tokuda – festvox.org Abstract This paper describes a hidden Markov model (HMM) based speech synthesis system developed for the Blizzard Challenge 2012. In the Blizzard Challenge 2012, we focused on a design of contexts for using audio books as training data and duration … Cited by 1 Related articles Cite Save More
The VUB Blizzard Challenge 2009 Entry L Latacz, W Mattheyses, W Verhelst – esat.kuleuven.be Abstract In this paper we describe the voices we submitted to the 2009 Blizzard Challenge, a yearly challenge to evaluate auditory speech synthesis on common data. Since it is the second time we participate in this challenge, in this paper we focus on the changes we … Related articles All 5 versions Cite Save More
The Blizzard Challenge 2013-Indian Language Tasks K Prahallad, A Vadapalli, N Elluru… – festvox.org Abstract The Blizzard challenge 2013 was the ninth annual Blizzard challenge which was organized by University of Edinburgh handling the English language tasks and IIIT Hyderabad handling the Indian language tasks. This paper decsribes the Indian language … Cite Save More
I 2 R’s Submission to Blizzard Challenge 2008 M Dong, D Zhu, B Ma, H Li – festvox.org Abstract This paper reports the I2R’s submission to the Blizzard Challenge 2008. This is our first participation in Blizzard Challenge. In this paper, we describe the approach that we used to build the three required voices. We introduced the acoustic parameters that … Related articles All 3 versions Cite Save More
I 2 R Text-to-Speech System for Blizzard Challenge 2013 SW Lee, M Dong, ST Ang, MM Chew – festvox.org Abstract This paper describes I2R’s submission to the Blizzard Challenge 2013 speech synthesis evaluation. There are two sections this year: an English audio book section, and an Indic language speech synthesis section. Unit-selection was used for the English task; … Cite Save More
MARY TTS unit selection and HMM-based voices for the Blizzard Challenge 2013 M Charfuelan, S Pammi, I Steiner – festvox.org Abstract This paper describes the implementation of a unit selection English voice and a HMM-based Hindi voice for our participation in the Blizzard Challenge 2013. The two voices have been created using the MARY TTS voice building framework. We describe how … Cite Save More
The USTC System for Blizzard Challenge 2011 CYY Ling-HuiChen, YJ Zhen-HuaLing – festvox.org Abstract This paper introduces the speech synthesis system developed by USTC for Blizzard Challenge 2011. USTC attended all the English tasks including a hub task and a spoke task. We developed a hidden Markov model (HMM) based unit selection system for both the … Related articles Cite Save More
The Speect text-to-speech system entry for the Blizzard Challenge 2013 JA Louw, GI Schlünz, W van der Walt, F de Wet… – festvox.org Abstract This paper describes the Speect text-to-speech system entry for the Blizzard Challenge 2013. The techniques applied for the tasks of the challenge are described as well as the implementation details for the alignment of the audio books and the text-to-speech … Cite Save More
The ILSP Text-to-Speech System for the Blizzard Challenge 2010 S Raptis, A Chalamandaris, P Tsiakoulis… – … . Blizzard Challenge …, 2010 – festvox.org Abstract This paper describes ILSP and INNOETICS Speech Synthesis System entry for the Blizzard Challenge 2012. A description of the underlying system and techniques used are provided, as well as information about the voice building process and discussion on the … Cited by 1 Related articles All 6 versions Cite Save More