9 papers
Continuous-Time Acoustic Modelling with Neural Controlled Differential Equations
Mattias Cross, Minghui Zhao, Anton Ragni
Text-to-speech (TTS) models commonly address text--speech alignment by expanding phone-level encoder states to frame-level decoder inputs using predicted durations. While this leng…
Decoding Order Matters in Autoregressive Speech Synthesis
Minghui Zhao, Anton Ragni
Autoregressive speech synthesis often adopts a left-to-right order, yet generation order is a modelling choice. We investigate decoding order through masked diffusion framework, wh…
A comparative study of generative models for child voice conversion
Protima Nomo Sudro, Anton Ragni, Thomas Hain
Generative models are a popular choice for adult-to-adult voice conversion (VC) because of their efficient way of modelling unlabelled data. To this point their usefulness in produ…
Discrete-Time Diffusion-Like Models for Speech Synthesis
Xiaozhou Tan, Minghui Zhao, Anton Ragni
Diffusion models have attracted a lot of attention in recent years. These models view speech generation as a continuous-time process. For efficient training, this process is typica…
Flowing Straighter with Conditional Flow Matching for Accurate Speech Enhancement
Mattias Cross, Anton Ragni
Current flow-based generative speech enhancement methods learn curved probability paths which model a mapping between clean and noisy speech. Despite impressive performance, the im…
Emphasis Sensitivity in Speech Representations
Shaun Cassini, Thomas Hain, Anton Ragni
This work investigates whether modern speech models are sensitive to prosodic emphasis - whether they encode emphasized and neutral words in systematically different ways. Prior wo…
What happens to diffusion model likelihood when your model is conditional?
Mattias Cross, Anton Ragni
Diffusion Models (DMs) iteratively denoise random samples to produce high-quality data. The iterative sampling process is derived from Stochastic Differential Equations (SDEs), all…
Training Data Augmentation for Dysarthric Automatic Speech Recognition by Text-to-Dysarthric-Speech Synthesis
Wing-Zin Leung, Mattias Cross, Anton Ragni +1
Automatic speech recognition (ASR) research has achieved impressive performance in recent years and has significant potential for enabling access for people with dysarthria (PwD) i…
Non-Intrusive Speech Intelligibility Prediction for Hearing-Impaired Users using Intermediate ASR Features and Human Memory Models
Rhiannon Mogridge, George Close, Robert Sutherland +4
Neural networks have been successfully used for non-intrusive speech intelligibility prediction. Recently, the use of feature representations sourced from intermediate layers of pr…