相关论文: Phrase break prediction with bidirectional encoder…

Discourse segmentation, which segments texts into Elementary Discourse Units, is a fundamental step in discourse analysis. Previous discourse segmenters rely on complicated hand-crafted features and are not practical in actual use. In this…

Recent advancements in end-to-end speech synthesis have made it possible to generate highly natural speech. However, training these models typically requires a large amount of high-fidelity speech data, and for unseen texts, the prosody of…

Vocoders received renewed attention as main components in statistical parametric text-to-speech (TTS) synthesis and speech transformation systems. Even though there are vocoding techniques give almost accepted synthesized speech, their high…

Sentence embedding is an important research topic in natural language processing (NLP) since it can transfer knowledge to downstream tasks. Meanwhile, a contextualized word representation, called BERT, achieves the state-of-the-art…

This report explores the use of paragraph break probability estimates to help predict the location of sentence breaks in English natural language text. We show that a sentence break predictor based almost solely on paragraph break…

While generative text-to-speech (TTS) models approach human-level quality, monolithic metrics fail to diagnose fine-grained acoustic artifacts or explain perceptual collapse. To address this, we propose TTS-PRISM, a multi-dimensional…

Recurrent neural networks have become ubiquitous in computing representations of sequential data, especially textual data in natural language processing. In particular, Bidirectional LSTMs are at the heart of several neural models achieving…

We proposed a~new accurate aspect extraction method that makes use of both word and character-based embeddings. We have conducted experiments of various models of aspect extraction using LSTM and BiLSTM including CRF enhancement on five…

While current Automated Essay Scoring (AES) methods demonstrate high scoring agreement with human raters, their decision-making mechanisms are not fully understood. Our proposed method, using counterfactual intervention assisted by Large…

Texting stands out as the most prominent form of communication worldwide. Individual spend significant amount of time writing whole texts to send emails or write something on social media, which is time consuming in this modern era. Word…

A text-mining-based word class categorization method and LSTM-based vocabulary pattern prediction method are introduced in this paper. A preprocessing method based on simple text appearance frequency analysis is first described. This method…

Though achieving impressive results on many NLP tasks, the BERT-like masked language models (MLM) encounter the discrepancy between pre-training and inference. In light of this gap, we investigate the contextual representation of…

Recently, denoising diffusion probabilistic models and generative score matching have shown high potential in modelling complex data distributions while stochastic calculus has provided a unified point of view on these techniques allowing…

Estimation of semantic similarity is an important research problem both in natural language processing and the natural language understanding, and that has tremendous application on various downstream tasks such as question answering,…

Smart word substitution aims to enhance sentence quality by improving word choices; however current benchmarks rely on human-labeled data. Since word choices are inherently subjective, ground-truth word substitutions generated by a small…

A recent line of research on spoken language assessment (SLA) employs neural models such as BERT and wav2vec 2.0 (W2V) to evaluate speaking proficiency across linguistic and acoustic modalities. Although both models effectively capture…

Learning high-quality sentence representations benefits a wide range of natural language processing tasks. Though BERT-based pre-trained language models achieve high performance on many downstream tasks, the native derived sentence…

In Japanese text-to-speech (TTS), it is necessary to add accent information to the input sentence. However, there are a limited number of publicly available accent dictionaries, and those dictionaries e.g. UniDic, do not contain many…

The purpose of the study is to investigate the relative effectiveness of four different sentiment analysis techniques: (1) unsupervised lexicon-based model using Sent WordNet; (2) traditional supervised machine learning model using logistic…

Prosody is essential for speech technology, shaping comprehension, naturalness, and expressiveness. However, current text-to-speech (TTS) systems still struggle to accurately capture human-like prosodic variation, in part because existing…