Learning to Say It Well: Reranking Realizations by Predicted Synthesis Quality
نویسندگان
چکیده
This paper presents a method for adapting a language generator to the strengths and weaknesses of a synthetic voice, thereby improving the naturalness of synthetic speech in a spoken language dialogue system. The method trains a discriminative reranker to select paraphrases that are predicted to sound natural when synthesized. The ranker is trained on realizer and synthesizer features in supervised fashion, using human judgements of synthetic voice quality on a sample of the paraphrases representative of the generator’s capability. Results from a cross-validation study indicate that discriminative paraphrase reranking can achieve substantial improvements in naturalness on average, ameliorating the problem of highly variable synthesis quality typically encountered with today’s unit selection synthesizers.
منابع مشابه
Error Estimation of Template-Based Protein Structure Models
The tertiary structure of proteins provides rich source of information for understanding protein function and evolution. Computational protein tertiary structure prediction has made significant progress over more than a decade due to the advancement of the techniques and the growth of sequence and structure databases. However, methods for assessing quality of predicted structure models are not ...
متن کاملModèle de traduction statistique à fragments enrichi par la syntaxe. (A Syntax-Augmented Phrase-Based Statistical Machine Translation Model)
Traditional Statistical Machine Translation models are not aware of linguistic structure. Thus, target lexical choices and word order are controlled only by surface-based statistics learned from the training corpus. Knowledge of linguistic structure can be beneficial since it provides generic information compensating data sparsity. The purpose of our work is to study the impact of syntactic inf...
متن کاملStatistical Ltag Parsing
STATISTICAL LTAG PARSING Libin Shen Aravind K. Joshi In this work, we apply statistical learning algorithms to Lexicalized Tree Adjoining Grammar (LTAG) parsing, as an effort toward statistical analysis over deep structures. LTAG parsing is a well known hard problem. Statistical methods successfully applied to LTAG parsing could also be used in many other structure prediction problems in NLP. F...
متن کاملA Survey On Visual Search Reranking
Due to the explosive growth of online video data and images , visual search is becoming an important area of research. Most existing approaches used text based image retrieval which is not so efficient. To precisely specify the visual documents, Visual search reranking is used. Visual search reranking is the rearrangement of visual documents based on initial search results or some external know...
متن کاملLow-Dimensional Discriminative Reranking
The accuracy of many natural language processing tasks can be improved by a reranking step, which involves selecting a single output from a list of candidate outputs generated by a baseline system. We propose a novel family of reranking algorithms based on learning separate low-dimensional embeddings of the task’s input and output spaces. This embedding is learned in such a way that prediction ...
متن کامل