Titlebook: Statistical Language and Speech Processing; Third International Adrian-Horia Dediu,Carlos Martín-Vide,Klára Vicsi Conference proceedings 2

广大

Evaluation of the Impact of Corpus Phonetic Alignment on the HMM-Based Speech Synthesis Quality,s conducted. Despite the degree of annotation changes, the synthetic speech quality of the five best systems remained close to that of the reference system, built upon the corpus whose labels were manually corrected.

amenity

加入

A Comparison of Human and Machine Estimation of Speaker Age,though if panels of listeners are consulted, human accuracy can be improved to a value closer to 7.5 years. Both human and machines have difficulty in accurately predicting the ages of older speakers.

不开心

Rhythm-Based Syllabic Stress Learning Without Labelled Data, algorithm using the same features. It showed that the system employing automatic labels has a performance close to the one using manual labels, with both classifiers outperforming the clustering algorithm.

范例

假装是我

Semi-extractive Multi-document Summarization via Submodular Functions,greedy algorithm to generate a summary which has a near optimal solution when its scoring functions are monotone nondecreasing and submodular. We use DUC 2007 dataset to evaluate our proposed method and the result shows improvement over two closely related works.

gerrymander

Lecture Notes in Computer Sciencehttp://image.papertrans.cn/s/image/876449.jpg

猛然一拉

https://doi.org/10.1007/978-3-319-25789-1distributional semantics; machine learning; natural language processing; neural networks; speech synthes

fulmination

forebear