Statistical parametric speech synthesis: from HMM to LSTM-RNN

By Heiga Zen. 2015

59 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. Lei He
8. Simon King

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, methodology): “Readers can refer to Zen [415], Zen et al. [418], Tokuda et al. [351] for some analyses on the advantages and drawbacks of HMM-based SPSS.”
• Merlin: An Open Source Neural Network Speech Synthesis System (2016, background): “Even though the naturalness of good waveform concatenation speech continues to be generally significantly better than that of wave-forms generated via SPSS using a vocoder, the advantages of flexibility, control, and small footprint mean that SPSS remains an attractive proposition.”
• Exploiting Syntactic Features in a Parsed Tree to Improve End-to-End TTS (2019, unknown): “New studies also tried to use syntactic parsing to improve HMM-or DNN-based acoustic models, e.g. [23], [24] and [25].”
• A New GAN-based End-to-End TTS Training Algorithm (2019, methodology): “From HMM [1] and DNN [2] to LSTM [3] and BLSTM [4], effective sequence modelling plays an important role in TTS.”
• Sequence-to-sequence Modelling of F0 for Speech Emotion Conversion (2019, methodology): “In particular LSTM-RNN networks have been used to model timbre and prosody variations over time, improving the speech quality over models [13] in text-to-speech synthesis [14, 15] and voice conversion [16, 17].”
• A Review of Deep Learning Based Speech Synthesis (2019, background): “It is well known that the acoustic features of a particular phoneme will be affected by the context information associated with the phoneme [30].”