Exploiting Acoustic and Syntactic Features for Prosody Labeling in a Maximum Entropy Framework

By Vivek Kumar Rangarajan Sridhar, Srinivas Bangalore, Shrikanth S. Narayanan. 2007

29 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Frank K. Soong
5. Zhizheng Wu
6. Lei Xie
7. Yi Ren
8. Yao Qian

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, methodology): “TTS Text Analysis Char→Linguistic TN [310, 223, 430], G2P [403, 320, 321] Prosody Prediction [312, 137, 277, 251] Unified Model [252, 437] DeepVoice 1/2 [8, 84]”
• Automatic prosody prediction for Chinese speech synthesis using BLSTM-RNN and embedding features (2015, background): “Some syntactic cues like part-of-speech (POS), syllable identity, syllable stress and their contextual counterparts are commonly used for prosody boundary prediction [3, 4, 5].”
• Automatic prosody prediction and detection with Conditional Random Field (CRF) models (2010, methodology): “Pitch, segmental duration, intensity and other acoustic correlates are generally adopted as assistants to prosody events detection [ 1-10 ].”
• Automatic Prosodic Labeling with Conditional Random Fields and Rich Acoustic Features (2008, methodology): “We employ a subset of the Boston Radio News Corpus (Ostendorf et al., 1995), employing data from speakers f1a, f2b, m1b, and m2b, for experimental consistency with (Chen et al., 2004; Rangara-jan Sridhar et al., 2007).”