Скачать с ютуб Triple M: A Practical Text-to-speech Synthesis System With Multi-guidance Attention And Multi-ba... в хорошем качестве

Triple M: A Practical Text-to-speech Synthesis System With Multi-guidance Attention And Multi-ba...

Title: Triple M: A Practical Text-to-speech Synthesis System With Multi-guidance Attention And Multi-band Multi-time LPCNet - (3 minutes introduction) Authors: Shilun Lin (Tencent, China), Fenglong Xie (Tencent, China), Li Meng (Tencent, China), Xinhui Li (Tencent, China), Li Lu (Tencent, China) Category: Speech Synthesis: Toward End-to-End Synthesis I Abstract: In this work, a robust and efficient text-to-speech (TTS) synthesis system named Triple M is proposed for large-scale online application. The key components of Triple M are: 1) A sequence-to-sequence model adopts a novel multi-guidance attention to transfer complementary advantages from guiding attention mechanisms to the basic attention mechanism without in-domain performance loss and online service modification. Compared with single attention mechanism, multi-guidance attention not only brings better naturalness to long sentence synthesis, but also reduces the word error rate by 26.8%. 2) A new efficient multi-band multi-time vocoder framework, which reduces the computational complexity from 2.8 to 1.0 GFLOP and speeds up LPCNet by 2.75× on a single CPU. For more details and PDF version of the paper visit: https://www.isca-speech.org/archive/i... d03s18t11trim