Prosodic Words Prediction from Lexicon Words with CRF and TBL Joint Method
نویسندگان
چکیده
Predicting prosodic words boundaries will directly influence the naturalness of synthetic speech, because prosodic word is at the lowest level of prosody hierarchy. In this paper, a Chinese prosodic phrasing method based on CRF and TBL model is proposed. First a CRF model is trained to predict the prosodic words boundaries from lexicon words. After that we apply a TBL based error driven learning approach to refine the results. The experiments shows that this joint method performs much better than HMM.
منابع مشابه
Prosodic Word Prediction Using a Maximum Entropy Approach
As the basic prosodic unit, the prosodic word influences the naturalness and the intelligibility greatly. Although the research shows that the lexicon word are greatly different from the prosodic word, the lexicon word still provides the important cues for the prosodic word forming. The rhythm constraint is another important factor for the prosodic word prediction. Some lexicon word length patt...
متن کاملIdentifying prosodic prominence patterns for English text-to-speech synthesis
This thesis proposes to improve and enrich the expressiveness of English Textto-Speech (TTS) synthesis by identifying and generating natural patterns of prosodic prominence. In most state-of-the-art TTS systems the prediction from text of prosodic prominence relations between words in an utterance relies on features that very loosely account for the combined effects of syntax, semantics, word i...
متن کاملMulti-Task Learning for Prosodic Structure Generation Using BLSTM RNN with Structured Output Layer
Prosodic structure generation from text plays an important role in Chinese text-to-speech (TTS) synthesis, which greatly influences the naturalness and intelligibility of the synthesized speech. This paper proposes a multi-task learning method for prosodic structure generation using bidirectional long shortterm memory (BLSTM) recurrent neural network (RNN) and structured output layer (SOL). Unl...
متن کاملDeep Structured Output Learning for Unconstrained Text Recognition
We develop a representation suitable for the unconstrained recognition of words in natural images, where unconstrained means that there is no fixed lexicon and words have unknown length. To this end we propose a convolutional neural network (CNN) based architecture which incorporates a Conditional Random Field (CRF) graphical model, taking the whole word image as a single input. The unaries of ...
متن کاملFinding Domain Specific Polar Words for Sentiment Classification
This paper presents a method of using conditional random fields (CRF) for extracting polar words and determining the overall sentiment of text. We frame sentiment classification as a feature selection problem and conduct three sets of experiments by using: prior polarity lexicons, bag-of-words classifiers and CRF sequence models. The results show the potential of utilizing CRFs in discovering h...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2006