COMBINING VOCAL TRACT LENGTH NORMALIZATION WITH HIERARCHIAL LINEAR TRANSFORMATIONS

Combining Vocal Tract Length Normalization with Hierarchical Linear Transformations

Lakshmi Babu Saheer, John David Scott Dines, Philip Neil Garner

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 shows that the merits of VTLN can be combined with those of linear transform based adaptation in a hierarchical Bayesian framework, where VTLN is used as the prior information. A novel technique for propagating the gender and age information captured by the VTLN transform into constrained structural maximum a posteriori linear regression (CSMAPLR) adaptation is presented. This paper also compares this proposed technique to other combination techniques. Experiments are performed on both matched and mismatched training and test conditions, including gender, age, and recording environments. Text-to-speech (TTS) synthesis experiments show that the resulting transformation produces improved speech quality with better naturalness and intelligibility (similar to VTLN transformation) when compared to the CSMAPLR transformation, especially when the quantity of adaptation data is very limited. With more parameters to capture speaker characteristics, the proposed method performs better in speaker similarity compared to VTLN in mis-matched conditions. Hence, the proposed combination combines the quality and intelligibility of VTLN with the speaker similarity of CSMAPLR especially in the mismatched train and test conditions. Experiments are also performed using the automatic speech recognition (ASR) system in a unified framework as that of synthesis. This is to prove that the techniques developed for TTS can be plugged into ASR in order to improve the performance.

2014

Combining Vocal Tract Length Normalization with Linear Transformations in a Bayesian Framework

Lakshmi Babu Saheer, John David Scott Dines, Philip Neil Garner

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. By contrast, with just a single parameter, VTLN captures very few speaker specific characteristics when compared to the available linear transform based adaptation techniques. This paper proposes that the merits of VTLN can be combined with those of linear transform based adaptation technique in a Bayesian framework, where VTLN is used as the prior information. A novel technique of propa- gating 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.

Idiap2012

Speaker adaptation and the evaluation of speaker similarity in the EMIME speech-to-speech translation project

Lakshmi Babu Saheer, John David Scott Dines, Philip Neil Garner, Matthew Gibson, Simon King, Hui Liang

This paper provides an overview of speaker adaptation research carried out in the EMIME speech-to-speech translation (S2ST) project. We focus on how speaker adaptation transforms can be learned from speech in one language and applied to the acous- tic models of another language. The adaptation is transferred across languages and/or from recognition models to synthesis models. The various approaches investigated can all be viewed as a process in which a mapping is defined in terms of either acoustic model states or linguistic units. The mapping is used to transfer either speech data or adaptation transforms between the two models. Because the success of speaker adaptation in text-to-speech synthesis is measured by judging speaker simi- larity, we also discuss issues concerning evaluation of speaker similarity in an S2ST scenario.

2010