Expressive, Variable, and Controllable Duration Modelling in TTS

06/28/2022
by   Ammar Abbas, et al.
0

Duration modelling has become an important research problem once more with the rise of non-attention neural text-to-speech systems. The current approaches largely fall back to relying on previous statistical parametric speech synthesis technology for duration prediction, which poorly models the expressiveness and variability in speech. In this paper, we propose two alternate approaches to improve duration modelling. First, we propose a duration model conditioned on phrasing that improves the predicted durations and provides better modelling of pauses. We show that the duration model conditioned on phrasing improves the naturalness of speech over our baseline duration model. Second, we also propose a multi-speaker duration model called Cauliflow, that uses normalising flows to predict durations that better match the complex target duration distribution. Cauliflow performs on par with our other proposed duration model in terms of naturalness, whilst providing variable durations for the same prompt and variable levels of expressiveness. Lastly, we propose to condition Cauliflow on parameters that provide an intuitive control of the pacing and pausing in the synthesised speech in a novel way.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/22/2016

Median-Based Generation of Synthetic Speech Durations using a Non-Parametric Approach

This paper proposes a new approach to duration modelling for statistical...
research
02/27/2023

Duration-aware pause insertion using pre-trained language model for multi-speaker text-to-speech

Pause insertion, also known as phrase break prediction and phrasing, is ...
research
04/16/2021

TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction

We propose TalkNet, a non-autoregressive convolutional neural model for ...
research
06/23/2021

Speech is Silver, Silence is Golden: What do ASVspoof-trained Models Really Learn?

We present our analysis of a significant data artifact in the official 2...
research
11/17/2017

Modelling dark current and hot pixels in imaging sensors

A gaussian mixture model was fitted to experimental data recorded under ...
research
10/08/2020

Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling

This paper presents Non-Attentive Tacotron based on the Tacotron 2 text-...
research
05/24/2023

Interactive Neural Resonators

In this work, we propose a method for the controllable synthesis of real...

Please sign up or login with your details

Forgot password? Click here to reset