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

Hwang, Min-Jae; Song, Eun Seop; Yamamoto, Ryōichi; Soong, Frank K.; Kang, Hong-Goo

doi:10.1109/icassp40776.2020.9053704

Cited by 8 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In typical lightweight neural vocoder where small model is adopted, it is necessary to adjust the sharpness of the output distributions to avoid noise caused by the random sampling process and achieve better quality. In FFTNet [18] and iLPCNet [19], lowering temperature in the voiced region with a constant factor is exploited for such purpose. Rather than using voiced information, LPCNet adopts pitch correlation to adjust the temperature factor.…”

Section: Generation Methodsmentioning

confidence: 99%

FeatherWave: An Efficient High-Fidelity Neural Vocoder with Multi-Band Linear Prediction

Tian

Zhang²,

Lu³

et al. 2020

Interspeech 2020

View full text Add to dashboard Cite

In this paper, we propose the FeatherWave, yet another variant of WaveRNN vocoder combining the multi-band signal processing and the linear predictive coding. The LPCNet, a recently proposed neural vocoder which utilized the linear predictive characteristic of speech signal in the WaveRNN architecture, can generate high quality speech with a speed faster than real-time on a single CPU core. However, LPCNet is still not efficient enough for online speech generation tasks. To address this issue, we adopt the multi-band linear predictive coding for WaveRNN vocoder. The multi-band method enables the model to generate several speech samples in parallel at one step. Therefore, it can significantly improve the efficiency of speech synthesis. The proposed model with 4 sub-bands needs less than 1.6 GFLOPS for speech generation. In our experiments, it can generate 24 kHz high-fidelity audio 9x faster than realtime on a single CPU, which is much faster than the LPCNet vocoder. Furthermore, our subjective listening test shows that the FeatherWave can generate speech with better quality than LPCNet.

show abstract

Section: Generation Methodsmentioning

confidence: 99%

FeatherWave: An Efficient High-Fidelity Neural Vocoder with Multi-Band Linear Prediction

Tian

Zhang²,

Lu³

et al. 2020

Interspeech 2020

View full text Add to dashboard Cite

show abstract

“…And we integrate frequencies from 0 to 24kHz into 50-dimensional filter banks, finer than the original Bark scale. of 16 kHz and some subsequent research has produced a 24 kHz LPCNet with higher fidelity synthesis [44], [47], [53], [54]. As described in Section I, we propose a Full-band LPCNet by introducing the following simple but effective modifications to synthesize high-fidelity speech waveforms with a sampling frequency of 48 kHz , which can cover the entire speech waveform and human auditory frequency ranges, using a CPU.…”

Section: Input Featuresmentioning

confidence: 99%

Full-Band LPCNet: A Real-Time Neural Vocoder for 48 kHz Audio With a CPU

et al. 2021

View full text Add to dashboard Cite

This paper investigates a real-time neural speech synthesis system on CPUs that can synthesize high-fidelity 48 kHz speech waveforms to cover the entire frequency range audible by human beings. Although most previous studies on 48 kHz speech synthesis have used traditional source-filter vocoders or a WaveNet vocoder for waveform generation, they have some drawbacks regarding synthesis quality or inference speed. LPCNet was proposed as a real-time neural vocoder with a mobile CPU but its sampling frequency is still only 16 kHz. In this paper, we propose a Full-band LPCNet to synthesize high-fidelity 48 kHz speech waveforms with a CPU by introducing some simple but effective modifications to the conventional LPCNet. We then evaluate the synthesis quality using both normal speech and a singing voice. The results of these experiments demonstrate that the proposed Full-band LPCNet is the only neural vocoder that can synthesize high-quality 48 kHz speech waveforms while maintaining real-time capability with a CPU.

show abstract

“…The created cascading network-based created system attains higher results compared to traditional structures. (M. Hwang et al, 2020) [22] improving the LPCNet vocoder performance by applying the linear prediction structured mixture density networks. In this process, an autoregressive neural vocoder examines the vocal source and vocal tract components.…”

Section: Background Studymentioning

confidence: 99%

Creating Speech Synthesis Process by Using Pulse Model in Log-Domain Vocoder With Whale Optimized Deep Convolution Neural Networks

Radha¹,

Vijayalakshmi²

2021

Preprint

View full text Add to dashboard Cite

Speech synthesis is an artificial production of human speech by utilizing computer systems called a speech synthesizer. Several statistical parameters are used in previous works to perform the speech synthesis process, but the vocoder is combined only the simpler model. Due to the lack of sequence of modeling, the quality degrading process is reducing the speech synthesis. Therefore, the Pulse model in log-domain vocoder with whale optimized deep convolution recurrent neural network is applied to investing the vocoder in this work. During this analysis, Mel-Generalized Cepstrum (MGC), maximum voice frequency (MVF), and F0 are applied to processing the signal to extracting the features, and the vocoder is generated successfully. The system's effectiveness is then evaluated using experimental results compared to deep neural networks and traditional recurrent networks.

show abstract

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

Cited by 8 publications

References 12 publications

FeatherWave: An Efficient High-Fidelity Neural Vocoder with Multi-Band Linear Prediction

FeatherWave: An Efficient High-Fidelity Neural Vocoder with Multi-Band Linear Prediction

Full-Band LPCNet: A Real-Time Neural Vocoder for 48 kHz Audio With a CPU

Creating Speech Synthesis Process by Using Pulse Model in Log-Domain Vocoder With Whale Optimized Deep Convolution Neural Networks

Contact Info

Product

Resources

About