Neural Hmms Are All You Need (for High-quality Attention-free TTS)

Abstract

Neural sequence-to-sequence TTS has achieved significantly better output quality than statistical speech synthesis using HMMs. However, neural TTS is generally not probabilistic and uses non-monotonic attention. Attention failures increase training time and can make synthesis babble incoherently. This paper describes how the old and new paradigms can be combined to obtain the advantages of both worlds, by replacing attention in neural TTS with an autoregressive left-right no-skip hidden Markov model defined by a neural network. Based on this proposal, we modify Tacotron 2 to obtain an HMM-based neural TTS model with monotonic alignment, trained to maximise the full sequence likelihood without approximation. We also describe how to combine ideas from classical and contemporary TTS for best results. The resulting example system is smaller and simpler than Tacotron 2, and learns to speak with fewer iterations and less data, whilst achieving comparable naturalness prior to the post-net. Ou

Stats

• citations9
• S2 citations—
• github stars0
• HF likes0
• heat score7.50
• arxiv keymehta2021neural

Related papers

• Robust Sequence-to-sequence Acoustic Modeling With Stepwise Monotonic Attention For Neural TTS (2019)11.49
• Feathertts: Robust And Efficient Attention Based Neural TTS (2020)5.84
• Prosody-controllable Spontaneous TTS With Neural Hmms (2022)8.09
• Neural Speech Synthesis With Transformer Network (2018)19.95
• Neural Sequence-to-sequence Speech Synthesis Using A Hidden Semi-markov Model Based Structured Attention Mechanism (2021)0.00
• MHTTS: Fast Multi-head Text-to-speech For Spontaneous Speech With Imperfect Transcription (2022)0.00
• Non-autoregressive TTS With Explicit Duration Modelling For Low-resource Highly Expressive Speech (2021)8.82
• Efficienttts: An Efficient And High-quality Text-to-speech Architecture (2020)0.00