Related papers: Automatic Prosody Prediction for Chinese Speech Sy…

Text-to-Speech synthesis systems are generally evaluated using Mean Opinion Score (MOS) tests, where listeners score samples of synthetic speech on a Likert scale. A major drawback of MOS tests is that they only offer a general measure of…

Conditional Random Field (CRF) and recurrent neural models have achieved success in structured prediction. More recently, there is a marriage of CRF and recurrent neural models, so that we can gain from both non-linear dense features and…

Although neural machine translation (NMT) has achieved impressive progress recently, it is usually trained on the clean parallel data set and hence cannot work well when the input sentence is the production of the automatic speech…

Syntactic structure of a sentence text is correlated with the prosodic structure of the speech that is crucial for improving the prosody and naturalness of a text-to-speech (TTS) system. Nowadays TTS systems usually try to incorporate…

Automatic speech recognition systems usually rely on spectral-based features, such as MFCC of PLP. These features are extracted based on prior knowledge such as, speech perception or/and speech production. Recently, convolutional neural…

A large part of the expressive speech synthesis literature focuses on learning prosodic representations of the speech signal which are then modeled by a prior distribution during inference. In this paper, we compare different prior…

Recent pretraining models in Chinese neglect two important aspects specific to the Chinese language: glyph and pinyin, which carry significant syntax and semantic information for language understanding. In this work, we propose ChineseBERT,…

End-to-end text-to-speech synthesis (TTS), which generates speech sounds directly from strings of texts or phonemes, has improved the quality of speech synthesis over the conventional TTS. However, most previous studies have been evaluated…

Prosody conveys rich emotional and semantic information of the speech signal as well as individual idiosyncrasies. We propose a stand-alone model that maps text-to-prosodic features such as F0 and energy and can be used in downstream tasks…

Acoustic word embeddings --- fixed-dimensional vector representations of variable-length spoken word segments --- have begun to be considered for tasks such as speech recognition and query-by-example search. Such embeddings can be learned…

In this paper, we present a cross-lingual voice cloning approach. BN features obtained by SI-ASR model are used as a bridge across speakers and language boundaries. The relationships between text and BN features are modeled by the latent…

For spoken dialog systems to conduct fluid conversational interactions with users, the systems must be sensitive to turn-taking cues produced by a user. Models should be designed so that effective decisions can be made as to when it is…

Previous work has modeled the compositionality of words by creating character-level models of meaning, reducing problems of sparsity for rare words. However, in many writing systems compositionality has an effect even on the…

Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality. Most NLG systems in common use employ rules and heuristics and tend to generate rigid and…

Statistical machine translation models have made great progress in improving the translation quality. However, the existing models predict the target translation with only the source- and target-side local context information. In practice,…

Chinese named entity recognition (CNER) is an important task in Chinese natural language processing field. However, CNER is very challenging since Chinese entity names are highly context-dependent. In addition, Chinese texts lack delimiters…

End-to-end models are favored in automatic speech recognition (ASR) because of its simplified system structure and superior performance. Among these models, recurrent neural network transducer (RNN-T) has achieved significant progress in…

Chinese traditional poetry is an important intangible cultural heritage of China and an artistic carrier of thought, culture, spirit and emotion. However, due to the strict rules of ancient poetry, it is very difficult to write poetry by…

Many recent studies have shown that the perception of speech can be decoded from brain signals and subsequently reconstructed as continuous language. However, there is a lack of neurological basis for how the semantic information embedded…

Despite prosody is related to the linguistic information up to the discourse structure, most text-to-speech (TTS) systems only take into account that within each sentence, which makes it challenging when converting a paragraph of texts into…