26 citations · 110 across the 16 of their papers we have counts for
18 papers
Differentiable Grey-box Modelling of Phaser Effects using Frame-based Spectral Processing
Alistair Carson, Cassia Valentini-Botinhao, Simon King +1
Machine learning approaches to modelling analog audio effects have seen intensive investigation in recent years, particularly in the context of non-linear time-invariant effects su…
Controllable Speaking Styles Using a Large Language Model
Atli Thor Sigurgeirsson, Simon King
Reference-based Text-to-Speech (TTS) models can generate multiple, prosodically-different renditions of the same target text. Such models jointly learn a latent acoustic space duri…
Ensemble prosody prediction for expressive speech synthesis
Tian Huey Teh, Vivian Hu, Devang S Ram Mohan +7
Generating expressive speech with rich and varied prosody continues to be a challenge for Text-to-Speech. Most efforts have focused on sophisticated neural architectures intended t…
Do Prosody Transfer Models Transfer Prosody?
Atli Thor Sigurgeirsson, Simon King
Some recent models for Text-to-Speech synthesis aim to transfer the prosody of a reference utterance to the generated target synthetic speech. This is done by using a learned embed…
Autovocoder: Fast Waveform Generation from a Learned Speech Representation using Differentiable Digital Signal Processing
Jacob J Webber, Cassia Valentini-Botinhao, Evelyn Williams +2
Most state-of-the-art Text-to-Speech systems use the mel-spectrogram as an intermediate representation, to decompose the task into acoustic modelling and waveform generation. A mel…
ADEPT: A Dataset for Evaluating Prosody Transfer
Alexandra Torresquintero, Tian Huey Teh, Christopher G. R. Wallis +6
Text-to-speech is now able to achieve near-human naturalness and research focus has shifted to increasing expressivity. One popular method is to transfer the prosody from a referen…
Ctrl-P: Temporal Control of Prosodic Variation for Speech Synthesis
Devang S Ram Mohan, Vivian Hu, Tian Huey Teh +6
Text does not fully specify the spoken form, so text-to-speech models must be able to learn from speech data that vary in ways not explained by the corresponding text. One way to r…
Using previous acoustic context to improve Text-to-Speech synthesis
Pilar Oplustil-Gallegos, Simon King
Many speech synthesis datasets, especially those derived from audiobooks, naturally comprise sequences of utterances. Nevertheless, such data are commonly treated as individual, un…
An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learning
Berrak Sisman, Junichi Yamagishi, Simon King +1
Speaker identity is one of the important characteristics of human speech. In voice conversion, we change the speaker identity from one to another, while keeping the linguistic cont…
Perception of prosodic variation for speech synthesis using an unsupervised discrete representation of F0
Zack Hodari, Catherine Lai, Simon King
In English, prosody adds a broad range of information to segment sequences, from information structure (e.g. contrast) to stylistic variation (e.g. expression of emotion). However,…
Comparison of Speech Representations for Automatic Quality Estimation in Multi-Speaker Text-to-Speech Synthesis
Jennifer Williams, Joanna Rownicka, Pilar Oplustil +1
We aim to characterize how different speakers contribute to the perceived output quality of multi-speaker Text-to-Speech (TTS) synthesis. We automatically rate the quality of TTS u…
Using generative modelling to produce varied intonation for speech synthesis
Zack Hodari, Oliver Watts, Simon King
Unlike human speakers, typical text-to-speech (TTS) systems are unable to produce multiple distinct renditions of a given sentence. This has previously been addressed by adding exp…
Attentive Filtering Networks for Audio Replay Attack Detection
Cheng-I Lai, Alberto Abad, Korin Richmond +3
An attacker may use a variety of techniques to fool an automatic speaker verification system into accepting them as a genuine user. Anti-spoofing methods meanwhile aim to make the…
Analysing Shortcomings of Statistical Parametric Speech Synthesis
Gustav Eje Henter, Simon King, Thomas Merritt +1
Output from statistical parametric speech synthesis (SPSS) remains noticeably worse than natural speech recordings in terms of quality, naturalness, speaker similarity, and intelli…
Exploring the robustness of features and enhancement on speech recognition systems in highly-reverberant real environments
José Novoa, Juan Pablo Escudero, Jorge Wuth +4
This paper evaluates the robustness of a DNN-HMM-based speech recognition system in highly-reverberant real environments using the HRRE database. The performance of locally-normali…
DNN-based Speech Synthesis for Indian Languages from ASCII text
Srikanth Ronanki, Siva Reddy, Bajibabu Bollepalli +1
Text-to-Speech synthesis in Indian languages has a seen lot of progress over the decade partly due to the annual Blizzard challenges. These systems assume the text to be written in…
Median-Based Generation of Synthetic Speech Durations using a Non-Parametric Approach
Srikanth Ronanki, Oliver Watts, Simon King +1
This paper proposes a new approach to duration modelling for statistical parametric speech synthesis in which a recurrent statistical model is trained to output a phone transition…
Improving Trajectory Modelling for DNN-based Speech Synthesis by using Stacked Bottleneck Features and Minimum Generation Error Training
Zhizheng Wu, Simon King
We propose two novel techniques --- stacking bottleneck features and minimum generation error training criterion --- to improve the performance of deep neural network (DNN)-based s…