Improving LPCNET-Based Text-to-Speech with Linear Prediction-Structured Mixture Density Network

By Min-Jae Hwang, Eunwoo Song, Ryuichi Yamamoto, Frank K. Soong, Hong-Goo Kang. 2020

14 citations recorded by the source corpus.

In this paper, we propose an improved LPCNet vocoder using a linear prediction (LP)-structured mixture density network (MDN). The recently proposed LPCNet vocoder has successfully achieved high-quality and lightweight speech synthesis systems by combining a vocal tract LP filter with a WaveRNN-based vocal source (i.e., excitation) generator. However, the quality of synthesized speech is often unstable because the vocal source component is insufficiently represented by the µ-law quantization method, and the model is trained without considering the entire speech production mechanism. To address this problem, we first introduce LP-MDN, which enables the autoregressive neural vocoder to structurally represent the interactions between the vocal tract and vocal source components. Then, we propose to incorporate the LP-MDN to the LPCNet vocoder by replacing the conventional discretized output with continuous density distribution. The experimental results verify that the proposed system provides high quality synthetic speech by achieving a mean opinion score of 4.41 within a text-to-speech framework.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

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

In Artificial Intelligence

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Frank K. Soong
5. Lei He
6. Sheng Zhao
7. Heng Lu
8. Qiao Tian

In Signal Processing

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Lei He
5. Frank K. Soong
6. Heng Lu
7. Nicholas Donald Lane
8. Shan Liu

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, background): “Some following works further improve LPCNet from different perspectives, such as reducing complexity for speedup [364, 269, 148], and improving stability for better quality [126].”
• Bunched LPCNet : Vocoder for Low-cost Neural Text-To-Speech Systems (2020, background): “It is one of the most compute efficient neural vocoders in recent times and has been demonstrated to give excellent performance when used in text-to-speech systems [4, 5] as well as in speech codecs [6].”
• FeatherWave: An efficient high-fidelity neural vocoder with multi-band linear prediction (2020, background): “In FFTNet [18] and iLPCNet [19], lowering temperature in the voiced region with a constant factor is exploited for such purpose.”
• An Efficient Subband Linear Prediction for LPCNet-Based Neural Synthesis (2020, methodology): “Besides, MDN with linear prediction presents a closed-loop so-lution to model the excitation and the subband samples in the first subband[15].”