Controllable Neural Text-to-speech Synthesis Using Intuitive Prosodic Features

Abstract

Modern neural text-to-speech (TTS) synthesis can generate speech that is indistinguishable from natural speech. However, the prosody of generated utterances often represents the average prosodic style of the database instead of having wide prosodic variation. Moreover, the generated prosody is solely defined by the input text, which does not allow for different styles for the same sentence. In this work, we train a sequence-to-sequence neural network conditioned on acoustic speech features to learn a latent prosody space with intuitive and meaningful dimensions. Experiments show that a model conditioned on sentence-wise pitch, pitch range, phone duration, energy, and spectral tilt can effectively control each prosodic dimension and generate a wide variety of speaking styles, while maintaining similar mean opinion score (4.23) to our Tacotron baseline (4.26).

Stats

• citations36
• S2 citations—
• github stars0
• HF likes0
• heat score11.76
• arxiv keyraitio2020controllable

Related papers

• Hierarchical Prosody Modeling And Control In Non-autoregressive Parallel Neural TTS (2021)8.35
• Prosody Transfer In Neural Text To Speech Using Global Pitch And Loudness Features (2019)0.00
• Sequence To Sequence Neural Speech Synthesis With Prosody Modification Capabilities (2019)9.59
• Prosody-controllable Spontaneous TTS With Neural Hmms (2022)8.09
• Emphasis Control For Parallel Neural TTS (2021)6.77
• Towards End-to-end Prosody Transfer For Expressive Speech Synthesis With Tacotron (2018)0.00
• Using Generative Modelling To Produce Varied Intonation For Speech Synthesis (2019)7.81
• Styletts: A Style-based Generative Model For Natural And Diverse Text-to-speech Synthesis (2022)10.97