Using decision trees within the tilt intonation model to predict F0 contours

Dusterhoff, Kurt E; Black, Alan W.; Taylor, Paul

doi:10.21437/eurospeech.1999-369

Cited by 34 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditionally, the pitch generation component is designed to support a specific abstract representation and is implemented after the representation is known. For example, given ToBI labeling, one may write a rule set to describe the f 0 shapes and their pitch values (Anderson et al 1984), or to use machine learning techniques to train the target values, including linear regression model (Black et al, 1996), CART tree models (Dusterhoff et al, 1999) and dynamical system models (Ross and Ostendorf, 1999). These pitch generation models are the decoders of ToBI, and will not support concepts that are not represented in ToBI.…”

Section: Literature Reviewmentioning

confidence: 99%

Prosody modeling with soft templates

Kochanski¹,

Shih²

2003

Speech Communication

View full text Add to dashboard Cite

Section: Literature Reviewmentioning

confidence: 99%

Prosody modeling with soft templates

Kochanski¹,

Shih²

2003

Speech Communication

View full text Add to dashboard Cite

“…Prosodic models in unit selection TTS systems have varied from rule based prescriptive models, based on an implicit or explicit knowledge base [1], to data driven models such as: CART decision trees trained from a speakers data [2,3], lazy learning approaches using tree matching e.g. [4], and unit selection based on a Viterbi search [5].…”

Section: Introductionmentioning

confidence: 99%

My voice, your prosody: sharing a speaker specific prosody model across speakers in unit selection TTS

Aylett¹,

Fackrell²,

Rutten³

2003

8th European Conference on Speech Communication and Technology (Eurospeech 2003)

View full text Add to dashboard Cite

Data sparsity is a major problem for data driven prosodic models. Being able to share prosodic data across speakers is a potential solution to this problem. This paper explores this potential solution by addressing two questions: 1) Does a larger less sparse model from a different speaker produce more natural speech than a small sparse model built from the original speaker? 2)Does a different speaker's larger model generate more unit selection errors than a small sparse model built from the original speaker?A unit selection approach is used to produce a lazy learning model of three English RP speaker's f0 and durational parameters. Speaker 1 (the target speaker) had a much smaller database (approximately one quarter to one fifth the size) of the other two. Speaker 2 was a female speaker with frequent mid phrase rises. Speaker 3 was a male speaker with a similar f0 range to speaker 1 and with a measured prosodic style suitable for news and financial text.We apply the models created for speaker 2 (an inappropriate model) and speaker 3 (an appropriate model) to speaker 1 and compare the results. Three passages (of three to four sentences in length) from challenging prosodic genres (news report, poetry and personal email) were synthesised using the target speaker and each of the three models. The synthesised utterances were played to 15 native english subjects and rated using a 5 point MOS scale. In addition, 7 experienced speech engineers rated each word for errors on a three point scale: 1. Acceptable, 2. Poor, 3. Unacceptable.The results suggest that a large model from an appropriate speaker does not sound more natural or produce fewer errors than a smaller model generated from the individual speaker's own data. In addition it shows that an inappropriate model does produce both less natural and more errors in the speech. High variance in both subject and materials analysis suggest both tests are far from ideal and that evaluation techniques for both error rate and naturalness need to improve.

show abstract

Reexamining the impact of information technology investment on productivity using regression tree and multivariate adaptive regression splines (MARS)

Osei-Bryson

2008

Inf Technol Manage

View full text Add to dashboard Cite

show abstract

Using decision trees within the tilt intonation model to predict F0 contours

Cited by 34 publications

References 6 publications

Prosody modeling with soft templates

Prosody modeling with soft templates

My voice, your prosody: sharing a speaker specific prosody model across speakers in unit selection TTS

Reexamining the impact of information technology investment on productivity using regression tree and multivariate adaptive regression splines (MARS)

Contact Info

Product

Resources

About