An investigation on linguistic features for Mandarin prosody generation

Hung, Yu-Ping; Yeh, Han-Yun; Liao, I-Bin; Pan, Chen-Ming; Chiang, Chen‐Yu

doi:10.1109/icsda.2014.7051426

Cited by 1 publication

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper focuses on the second problem to extend and elaborate on our previous research pertaining to PC [28][29][30][31] and QC [30,31] features. A more substantial analysis and modeling details are provided in this paper to provide readers with an insight into the proposed PC and QC features, the design of which is influenced by automatic Chinese punctuation generation [32] and the linguistic characteristic of the Chinese punctuation system [33].…”

Section: Introductionmentioning

confidence: 99%

“…Some studies have improved the accuracy of prosodic structure prediction or prosodic-acoustic feature prediction by incorporating higher-level syntactic features, such as word chunks [16] and syntactic trees [16,26,27]. Moreover, statistical linguistic features such as connective degree [14], punctuation confidence (PC) [28][29][30][31], and quotation confidence (QC) [30,31] have been proposed to neglect complex syntactic tree parsing and manual word chunking that is impractical when constructing an unlimited-text MTTS.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, the punctuation generation of a speaker when reading written Chinese reflects the speaker's prosodic phrasing strategy because pause breaks are highly correlated with some MPMs, such as the period, comma, exclamatory mark, question mark, semicolon, and colon. Therefore, an automatic punctuation generation model that predicts MPMs and is trained by using a large text corpus can learn punctuation strategies for predicting MPMs from various contributors for providing useful cues for predictions of both prosodic breaks [28,31] and prosodic-acoustic features [29][30][31].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Punctuation-generation-inspired linguistic features for Mandarin prosody generation

Chiang

Hung

Yeh

et al. 2019

J AUDIO SPEECH MUSIC PROC.

Self Cite

View full text Add to dashboard Cite

This paper proposes two novel linguistic features extracted from text input for prosody generation in a Mandarin text-to-speech system. The first feature is the punctuation confidence (PC), which measures the likelihood that a major punctuation mark (MPM) can be inserted at a word boundary. The second feature is the quotation confidence (QC), which measures the likelihood that a word string is quoted as a meaningful or emphasized unit. The proposed PC and QC features are influenced by the properties of automatic Chinese punctuation generation and linguistic characteristic of the Chinese punctuation system. Because MPMs are highly correlated with prosodicacoustic features and quoted word strings serve crucial roles in human language understanding, the two features could potentially provide useful information for prosody generation. This idea was realized by employing conditional random-field-based models for predicting MPMs, quoted word string locations, and their associated confidences-that is, PC and QC-for each word boundary. The predicted punctuations and their confidences were then combined with traditional linguistic features to predict prosodic-acoustic features for performing speech synthesis using multilayer perceptrons. Both objective and subjective tests demonstrated that the prosody generated with the proposed linguistic features was superior to that generated without the proposed features. Therefore, the proposed PC and QC are identified as promising features for Mandarin prosody generation.

show abstract