.png){kind=icon}
返回
Parallel Synthesis for Autoregressive Speech Generation
.png){kind=icon}
OA
AI
DOI：10.1109/TASLP.2023.3301212.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Autoregressive neural vocoders have achieved outstanding performance in speech synthesis tasks such as text-to-speech and voice conversion. An autoregressive vocoder predicts a sample at some time step conditioned on those at previous time steps. Though it synthesizes natural human speech, the iterative generation inevitably makes the synthesis time proportional to the utterance length, leading to low efficiency. Many works were dedicated to generating the whole speech sequence in parallel and proposed GAN-based, flow-based, and score-based vocoders. This paper proposed a new thought for the autoregressive generation. Instead of iteratively predicting samples in a time sequence, the proposed model performs frequency-wise autoregressive generation (FAR) and bit-wise autoregressive generation (BAR) to synthesize speech. In FAR, a speech utterance is split into frequency subbands, and a subband is generated conditioned on the previously generated one. Similarly, in BAR, an 8-bit quantized signal is generated iteratively from the first bit. By redesigning the autoregressive method to compute in domains other than the time domain, the number of iterations in the proposed model is no longer proportional to the utterance length but to the number of subbands/bits, significantly increasing inference efficiency. Besides, a post-filter is employed to sample signals from output posteriors; its training objective is designed based on the characteristics of the proposed methods. Experimental results show that the proposed model can synthesize speech faster than real-time without GPU acceleration. Compared with baseline vocoders, the proposed model achieves better MUSHRA results and shows good generalization ability for unseen speakers and 44 kHz speech.
Keyword:
Vocoder
neural network
neural speech synthesis
autoregressive model
期刊
I
IF:
5.1
论文数:
2.6K
被引数:
1.1W
机构
引用论文
Responses of some herbaceous road-side wild plant species against ambient particulate pollution (PM10): A case study from Malda district, West Bengal一些草本道路旁野生植物物种对环境颗粒物污染(PM10)的响应：来自印度西孟加拉邦马勒达区的一个案例研究.png)
PleioneOAAI
PleioneIF0
OAAI分享收藏Ephedra strongylensis (Ephedraceae), a new species from Aeolian islands (Sicily)Ephedra strongylensis (Ephedraceae)，一种来自埃奥利安群岛（西西里）的新物种。Phytotaxa
PhytotaxaIF0
PREAI
分享收藏Identification and characterization of a TLR13 gene homologue from Laodelphax striatellus involved in the immune response induced by rice stripe virus鉴定和表征来自条纹水稻病病毒诱导的免疫反应中涉及的Laodelphax striatellus的TLR13基因同源物
OAAI
OAAI分享收藏
查看更多内容