Damien Lolive

Learn More
This article describes a F 0 curve estimation scheme based on a B-spline model 1. We compare this model with more classical spline representation. The free parameters of both models are the number of knots and their location. An optimal location is proposed using a simulated an-nealing strategy. Experiments on real F 0 curves confirm the adequacy and good(More)
This article describes a new unsupervised methodology to learn F0 classes using HMM on a syllable basis. A F0 class is represented by a HMM with three emitting states. The unsupervised clustering algorithm relies on an iterative gaussian splitting and EM retraining process. First, a single class is learnt on a training corpus (8000 syllables) and it is then(More)
This article describes a new unsupervised methodology to learn F0 classes using HMM models on a syllable basis. A F0 class is represented by a HMM with three emitting states. The clustering algorithm relies on an iterative gaussian splitting and EM retraining process. First, a single class is learnt on a training corpus (8000 syllables) and it is then(More)