F0 modeling with multi-layer additive modeling based on a statistical learning technique
نویسنده
چکیده
In this paper, we describe research in fundamental frequency modeling based on a statistical learning technique called additive models. A two-layer additive F0 model consists of a long-term, intonational phrase-level component, and a short-term, accentual phrase-level component. It can be learned from the data using a backfitting algorithm, an optimizer of a penalized least-square criterion defined on the model. It estimates two components simultaneously by iteratively applying cubic spline smoothers. To investigate the further flexibility of the model, we incorporated a third additive term that represents a contextual effect on an accentual phrase, and confirmed the improvements in terms of RMS errors. Experimental results on a 7,000 utterance Japanese speech corpus shows an achievement of F0 RMS errors of 28.5 and 29.3 Hz on the training and test data, respectively, with corresponding correlation coefficients of 0.81 and 0.79.
منابع مشابه
Fundamental Frequency Modeling for Speech Synthesis Based on a Statistical Learning Technique
This paper proposes a novel multi-layer approach to fundamental frequency modeling for concatenative speech synthesis based on a statistical learning technique called additive models. We define an additive F0 contour model consisting of long-term, intonational phrase-level, component and short-term, accentual phrase-level, component, along with a least-squares error criterion that includes a re...
متن کاملFundamental Frequency Modeling for Corpus-based Speech Synthesis Based on a Statistical Learning Technique
This paper proposes a novel two-layer approach to fundamental frequency modeling for concatenative speech synthesis based on a statistical learning technique called additive models. We define an additive F0 contour model consisting of long-term, intonational phrase-level, component and short-term, accentual phrase-level, component, along with a least-squares error criterion that includes a regu...
متن کاملIntelligent multi-agent modeling of the interbank network and evaluation of the impact of regulatory policies
agent-based modeling is an emerging computational technique that makes it possible to simulate complex economic systems, including the banking network, with a bottom-up approach. In this paper, the country's banking network is simulated with an intelligent multi-agent modeling model and indicates that these agents behave based on the adaptive learning. This modeling has been done with the aim o...
متن کاملStatistical physics modeling of equilibrium adsorption of cadmium ions onto activated carbon, chitosan and chitosan/activated carbon composite
The adsorption ability of activated carbon, chitosan, and chitosan/activated carbon composite for cadmium separation from aqueous solution was analyzed via statistical physical modeling. The equilibrium data were analyzed by Langmuir, Hill, double layer model, and the multi-layer model with saturation isotherm models. Results showed that the multi-layer model with saturation could well describe...
متن کاملA hierarchical F0 modeling method for HMM-based speech synthesis
The conventional state-based F0 modeling in HMM-based speech synthesis system is good at capturing micro prosodic features, but difficult to characterize long term pitch patterns directly. This paper presents a hierarchical F0 modeling method to address this issue. In this method, different F0 models are used to model the pitch patterns for different prosodic layers (including state, phone, syl...
متن کامل