Introduce Segmeantal Inner Timewarping into Parametric Trajectory Segment Model for LVCSR
نویسنده
چکیده
In this paper, a parametric trajectory segment model (PTSM) with segmental inner time warping is proposed to improve the recognition accuracy of large vocabulary continuous speech recognition(LVCSR). The proposed PTSM utilizes the state boundary information provided by HMM system during decoding to do segmental inner time warping. Good alignment between different length realizations of a same phone unit can be obtained by this method. Based on the effective alignment, a new distance measure of measuring the average value of the norm of the residual error is used in k-means clustering to decide the parameters of the mixture density of PTSM. For two LVCSR tasks, the HMM system working with the proposed PTSM can give a consistent improvement over either the HMM system working with the traditional PTSM or the HMM system working alone.
منابع مشابه
Parametric trajectory mixtures for LVCSR
Parametric trajectory models explicitly represent the temporal evolution of the speech features as a Gaussian process with time-varying parameters. HMMs are a special case of such models, one in which the trajectory constraints in the speech segment are ignored by the assumption of conditional independence across frames within the segment. In this paper, we investigate in detail some extensions...
متن کاملImproving Parametric Traj Integration of Pitch And
This paper presents the application of pitch/tone information to improve Parametric Trajectory Modeling (PTM). To simulate the trajectory of pitch in a segment in PTM recognizer, we in fact get its corresponding tone information. From another point of view, tone is a segmental feature and PTM has the excellent framework to incorporate it. So we here introduce the “soft” and “hard” integration m...
متن کاملConstructing Skill Trees for Reinforcement Learning Agents from Demonstration Trajectories
We introduce CST, an algorithm for constructing skill trees from demonstration trajectories in continuous reinforcement learning domains. CST uses a changepoint detection method to segment each trajectory into a skill chain by detecting a change of appropriate abstraction, or that a segment is too complex to model as a single skill. The skill chains from each trajectory are then merged to form ...
متن کاملPseudospectral Model Predictive Control under Partially Learned Dynamics
Trajectory optimization of a controlled dynamical system is an essential part of autonomy, however many trajectory optimization techniques are limited by the fidelity of the underlying parametric model. In the field of robotics, a lack of model knowledge can be overcome with machine learning techniques, utilizing measurements to build a dynamical model from the data. This paper aims to take the...
متن کاملPsychoacoustic Segment Scoring for Multi-Form Speech Synthesis
In multi-form segment synthesis, output speech is constructed by splicing waveform segments with statistically modeled and regenerated parametric speech segments. The fraction of model-derived segments is called model-template ratio. The motivation of this work is to further increase flexibility of multi-form synthesis maintaining high speech quality for high model-template ratios. An approach ...
متن کامل