VTLN adaptation for statistical speech synthesis

Saheer, Lakshmi Babu; Garner, Philip N.; Dines, John; Liang, Hui

doi:10.1109/icassp.2010.5495126

Cited by 17 publications

(20 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The characteristics estimated by VTLN when propagated to the nodes of the tree structure are expected to improve the speaker specific transform estimation for CSMAPLR. More specifically, VTLN has been shown to be closer to the average voice, and hence better in naturalness [3] and CSMAPLR is known to bring in better speaker similarity when very little adaptation data is available. Apriori, combination of these two is expected to give improved performance with respect to naturalness and speaker similarity.…”

Section: Using Vtln As Csmaplr Priormentioning

confidence: 99%

“…The main advantage of using the EM algorithm over, say, a grid search is that the resulting warping factor estimation has finer granularity of α values, and efficient implementation in time and space. The EM algorithm can be embedded into HMM training utilizing the same sufficient statistics as CMLLR [3,5,14], which transforms the spectral features as follows…”

Section: Vtln In Statistical Parametric Speech Synthesismentioning

confidence: 99%

“…These techniques require a considerable amount of adaptation data (of the order of tens of utterances) for reasonable adaptation performance. Rapid adaptation techniques like vocal tract length normalization (VTLN) have also been successfully applied to statistical parametric speech synthesis [3]. By contrast, this technique requires very little adaptation data Thanks to FP7 Emime project for funding.…”

Section: Introductionmentioning

confidence: 99%

“…Initial investigations of VTLN for statistical parametric speech synthesis were performed by Saheer et.al. [3,8].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Combining vocal tract length normalization with hierarchial linear transformations

Saheer

Yamagishi

Garner

et al. 2012

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Recent research has demonstrated the effectiveness of vocal tract length normalization (VTLN) as a rapid adaptation technique for statistical parametric speech synthesis. VTLN produces speech with naturalness preferable to that of MLLR-based adaptation techniques, being much closer in quality to that generated by the original average voice model. However with only a single parameter, VTLN captures very few speaker specific characteristics when compared to linear transform based adaptation techniques. This paper proposes that the merits of VTLN can be combined with those of linear transform based adaptation in a hierarchial Bayesian framework, where VTLN is used as the prior information. A novel technique for propagating the gender information from the VTLN prior through constrained structural maximum a posteriori linear regression (CSMAPLR) adaptation is presented. Experiments show that the resulting transformation has improved speech quality with better naturalness, intelligibility and improved speaker similarity.Index Terms-Statistical parametric speech synthesis, hidden Markov models, speaker adaptation, vocal tract length normalization, constrained structural maximum a posteriori linear regression

show abstract

Section: Using Vtln As Csmaplr Priormentioning

confidence: 99%

Section: Vtln In Statistical Parametric Speech Synthesismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Initial investigations of VTLN for statistical parametric speech synthesis were performed by Saheer et.al. [3,8].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Combining vocal tract length normalization with hierarchial linear transformations

Saheer

Yamagishi

Garner

et al. 2012

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…VTLN has been applied to HMM based speech synthesis [8] and has been shown to improve the synthetic speech quality when combined with adaptation based approaches [9,10]. Using VTLN as a linear transformation eliminates the need to store warped features.…”

Section: Vtln Adaptation For Speech Synthesismentioning

confidence: 99%

Creating synthetic voices for children by adapting adult average voice using stacked transformations and VTLN

Karhila

Sanand

Kurimo

et al. 2012

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This paper describes experiments in creating personalised children's voices for HMM-based synthesis by adapting either an adult or child average voice. The adult average voice is trained from a large adult speech database, whereas the child average voice is trained using a small database of children's speech. Here we present the idea to use stacked transformations for creating synthetic child voices, where the child average voice is first created from the adult average voice through speaker adaptation using all the pooled speech data from multiple children and then adding child specific speaker adaptation on top of it. VTLN is applied to speech synthesis to see whether it helps the speaker adaptation when only a small amount of adaptation data is available. The listening test results show that the stacked transformations significantly improve speaker adaptation for small amounts of data, but the additional benefit provided by VTLN is not yet clear.

show abstract

Current trends in multilingual speech processing

Bourlard

Dines

Magimai-Doss

et al. 2011

Sadhana

Self Cite

View full text Add to dashboard Cite

Abstract. In this paper, we describe recent work at Idiap Research Institute in the domain of multilingual speech processing and provide some insights into emerging challenges for the research community. Multilingual speech processing has been a topic of ongoing interest to the research community for many years and the field is now receiving renewed interest owing to two strong driving forces. Firstly, technical advances in speech recognition and synthesis are posing new challenges and opportunities to researchers. For example, discriminative features are seeing wide application by the speech recognition community, but additional issues arise when using such features in a multilingual setting. Another example is the apparent convergence of speech recognition and speech synthesis technologies in the form of statistical parametric methodologies. This convergence enables the investigation of new approaches to unified modelling for automatic speech recognition and text-to-speech synthesis (TTS) as well as cross-lingual speaker adaptation for TTS. The second driving force is the impetus being provided by both government and industry for technologies to help break down domestic and international language barriers, these also being barriers to the expansion of policy and commerce. Speech-to-speech and speech-to-text translation are thus emerging as key technologies at the heart of which lies multilingual speech processing.

show abstract

VTLN adaptation for statistical speech synthesis

Cited by 17 publications

References 12 publications

Combining vocal tract length normalization with hierarchial linear transformations

Combining vocal tract length normalization with hierarchial linear transformations

Creating synthetic voices for children by adapting adult average voice using stacked transformations and VTLN

Current trends in multilingual speech processing

Contact Info

Product

Resources

About