Multisyn: Open-domain unit selection for the Festival speech synthesis system

Clark, Robert A.; Richmond, Korin; King, Simon

doi:10.1016/j.specom.2007.01.014

Cited by 113 publications

(93 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the 2007 Blizzard Challenge, Festival's new "Multisyn" module [72], which provides a flexible, general implementation of unit selection and a set of associated voice building tools, was used. HTS-2007 used the existing modules from Festival, resulting in different phonesets and front-end text-processing outputs.…”

Section: Results Of the Blizzard Challenge 2007mentioning

confidence: 99%

Robust Speaker-Adaptive HMM-Based Text-to-Speech Synthesis

Yamagishi

Nose

Zen

et al. 2009

IEEE Trans. Audio Speech Lang. Process.

Self Cite

158

103

View full text Add to dashboard Cite

Abstract-This paper describes a speaker-adaptive HMM-based speech synthesis system. The new system, called "HTS-2007," employs speaker adaptation (CSMAPLR+MAP), feature-space adaptive training, mixed-gender modeling, and full-covariance modeling using CSMAPLR transforms, in addition to several other techniques that have proved effective in our previous systems. Subjective evaluation results show that the new system generates significantly better quality synthetic speech than speaker-dependent approaches with realistic amounts of speech data, and that it bears comparison with speaker-dependent approaches even when large amounts of speech data are available. In addition, a comparison study with several speech synthesis techniques shows the new system is very robust: It is able to build voices from less-than-ideal speech data and synthesize good-quality speech even for out-of-domain sentences.

show abstract

Section: Results Of the Blizzard Challenge 2007mentioning

confidence: 99%

Robust Speaker-Adaptive HMM-Based Text-to-Speech Synthesis

Yamagishi

Nose

Zen

et al. 2009

IEEE Trans. Audio Speech Lang. Process.

Self Cite

158

103

View full text Add to dashboard Cite

show abstract

“…1) CART, as used by the Festival speech synthesizer [28]; 2) JMM, since this exhibited good performance [17], [26]; 3) CRF, as proposed here. For the CART-based system, we followed the training process in [29] in which an allowable table that specifies the allowable pronunciations of each letter is manually created using trial & error, and a CART is learned for each letter, with configuration settings (especially the "stop value") chosen to optimize performance on the development set.…”

Section: A Experimental Settingsmentioning

confidence: 99%

Letter-to-Sound Pronunciation Prediction Using Conditional Random Fields

Wang

King

2011

IEEE Signal Process. Lett.

Self Cite

View full text Add to dashboard Cite

Abstract-Pronunciation prediction, or letter-to-sound (LTS) conversion, is an essential task for speech synthesis, open vocabulary spoken term detection and other applications dealing with novel words. Most current approaches (at least for English) employ data-driven methods to learn and represent pronunciation "rules" using statistical models such as decision trees, hidden Markov models (HMMs) or joint-multigram models (JMMs). The LTS task remains challenging, particularly for languages with a complex relationship between spelling and pronunciation such as English. In this paper, we propose to use a conditional random field (CRF) to perform LTS because it avoids having to model a distribution over observations and can perform global inference, suggesting that it may be more suitable for LTS than decision trees, HMMs or JMMs. One challenge in applying CRFs to LTS is that the phoneme and grapheme sequences of a word are generally of different lengths, which makes CRF training difficult. To solve this problem, we employed a joint-multigram model to generate aligned training exemplars. Experiments conducted with the AMI05 dictionary demonstrate that a CRF significantly outperforms other models, especially if n-best lists of predictions are generated.

show abstract

“…For comparison, performance using a class and regression tree (CART) model -the default method for LTS used by the Festival speech synthesis system [56] -is reported as well. JMM generally outperforms the CART.…”

Section: A Jmm-based 1-best Pronunciation Predictionmentioning

confidence: 99%

Stochastic Pronunciation Modeling for Out-of-Vocabulary Spoken Term Detection

Wang

King

Frankel

2011

IEEE Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

Abstract-Spoken term detection (STD) is the name given to the task of searching large amounts of audio for occurrences of spoken terms, which are typically single words or short phrases. One reason that STD is a hard task is that search terms tend to contain a disproportionate number of out-of-vocabulary (OOV) words. The most common approach to STD uses subword units. This, in conjunction with some method for predicting pronunciations of OOVs from their written form, enables the detection of OOV terms but performance is considerably worse than for in-vocabulary terms. This performance differential can be largely attributed to the special properties of OOVs.One such property is the high degree of uncertainty in the pronunciation of OOVs. We present a stochastic pronunciation model (SPM) which explicitly deals with this uncertainty. The key insight is to search for all possible pronunciations when detecting an OOV term, explicitly capturing the uncertainty in pronunciation. This requires a probabilistic model of pronunciation, able to estimate a distribution over all possible pronunciations. We use a joint-multigram model (JMM) for this and compare the JMM-based SPM with the conventional soft match approach. Experiments using speech from the meetings domain demonstrate that the SPM performs better than soft match in most operating regions, especially at low false alarm probabilities. Furthermore, SPM and soft match are found to be complementary: their combination provides further performance gains.

show abstract

Multisyn: Open-domain unit selection for the Festival speech synthesis system

Cited by 113 publications

References 21 publications

Robust Speaker-Adaptive HMM-Based Text-to-Speech Synthesis

Robust Speaker-Adaptive HMM-Based Text-to-Speech Synthesis

Letter-to-Sound Pronunciation Prediction Using Conditional Random Fields

Stochastic Pronunciation Modeling for Out-of-Vocabulary Spoken Term Detection

Contact Info

Product

Resources

About