mlsanityData to 7 Oct 2026

Triple M: A Practical Text-to-speech Synthesis System With Multi-guidance Attention And Multi-band Multi-time LPCNet

arXiv 2102.00247 ↗First posted 30 Jan 2021cs.CL eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

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 2.75x on a single CPU.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 25 references that are in the map. First posted on arXiv 30 Jan 2021.

Builds on

16 of 25 references.

References · 16

  1. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  2. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  3. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  4. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  5. 2013Generating Sequences With Recurrent Neural Networkscited by 549
  6. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 487
  7. 2018Efficient Neural Audio Synthesiscited by 218
  8. 2017Parallel WaveNet: Fast High-Fidelity Speech Synthesiscited by 214
  9. 2018LPCNet: Improving Neural Speech Synthesis Through Linear Predictioncited by 109
  10. 2018ClariNet: Parallel Wave Generation in End-to-End Text-to-Speechcited by 70
  11. 2019Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesiscited by 44
  12. 2019Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTScited by 33
4 more
  1. 2019DurIAN: Duration Informed Attention Network For Multimodal Synthesiscited by 33
  2. 2018Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesiscited by 17
  3. 2020Bunched LPCNet : Vocoder for Low-cost Neural Text-To-Speech Systemscited by 16
  4. 2020JDI-T: Jointly trained Duration Informed Transformer for Text-To-Speech without Explicit Alignmentcited by 13

Built on by

Not cited yet.