82 citations · 396 across the 52 of their papers we have counts for
61 papers
BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data
Mateusz Łajszczak, Guillermo Cámbara, Yang Li +16
We introduce a text-to-speech (TTS) model called BASE TTS, which stands for ig daptive treamable TTS with mergent abilities. BASE TT…
A Comparative Analysis of Pretrained Language Models for Text-to-Speech
Marcel Granero-Moya, Penny Karanasou, Sri Karlapati +4
State-of-the-art text-to-speech (TTS) systems have utilized pretrained language models (PLMs) to enhance prosody and create more natural-sounding speech. However, while PLMs have b…
Controllable Emphasis with zero data for text-to-speech
Arnaud Joly, Marco Nicolis, Ekaterina Peterova +11
We present a scalable method to produce high quality emphasis for text-to-speech (TTS) that does not require recordings or annotations. Many TTS models include a phoneme duration m…
eCat: An End-to-End Model for Multi-Speaker TTS & Many-to-Many Fine-Grained Prosody Transfer
Ammar Abbas, Sri Karlapati, Bastian Schnell +7
We present eCat, a novel end-to-end multispeaker model capable of: a) generating long-context speech with expressive and contextually appropriate prosody, and b) performing fine-gr…
Computer-assisted Pronunciation Training -- Speech synthesis is almost all you need
Daniel Korzekwa, Jaime Lorenzo-Trueba, Thomas Drugman +1
The research community has long studied computer-assisted pronunciation training (CAPT) methods in non-native speech. Researchers focused on studying various model architectures, s…
Simple and Effective Multi-sentence TTS with Expressive and Coherent Prosody
Peter Makarov, Ammar Abbas, Mateusz Łajszczak +5
Generating expressive and contextually appropriate prosody remains a challenge for modern text-to-speech (TTS) systems. This is particularly evident for long, multi-sentence inputs…
Expressive, Variable, and Controllable Duration Modelling in TTS
Ammar Abbas, Thomas Merritt, Alexis Moinet +5
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 rely…
CopyCat2: A Single Model for Multi-Speaker TTS and Many-to-Many Fine-Grained Prosody Transfer
Sri Karlapati, Penny Karanasou, Mateusz Lajszczak +7
In this paper, we present CopyCat2 (CC2), a novel model capable of: a) synthesizing speech with different speaker identities, b) generating speech with expressive and contextually…
Distribution augmentation for low-resource expressive text-to-speech
Mateusz Lajszczak, Animesh Prasad, Arent van Korlaar +8
This paper presents a novel data augmentation technique for text-to-speech (TTS), that allows to generate new (text, audio) training examples without requiring any additional data.…
Multi-Scale Spectrogram Modelling for Neural Text-to-Speech
Ammar Abbas, Bajibabu Bollepalli, Alexis Moinet +6
We propose a novel Multi-Scale Spectrogram (MSS) modelling approach to synthesise speech with an improved coarse and fine-grained prosody. We present a generic multi-scale spectrog…
Voicy: Zero-Shot Non-Parallel Voice Conversion in Noisy Reverberant Environments
Alejandro Mottini, Jaime Lorenzo-Trueba, Sri Vishnu Kumar Karlapati +1
Voice Conversion (VC) is a technique that aims to transform the non-linguistic information of a source utterance to change the perceived identity of the speaker. While there is a r…
A learned conditional prior for the VAE acoustic space of a TTS system
Penny Karanasou, Sri Karlapati, Alexis Moinet +5
Many factors influence speech yielding different renditions of a given sentence. Generative models, such as variational autoencoders (VAEs), capture this variability and allow mult…
Weakly-supervised word-level pronunciation error detection in non-native English speech
Daniel Korzekwa, Jaime Lorenzo-Trueba, Thomas Drugman +2
We propose a weakly-supervised model for word-level mispronunciation detection in non-native (L2) English speech. To train this model, phonetically transcribed L2 speech is not req…
Mispronunciation Detection in Non-native (L2) English with Uncertainty Modeling
Daniel Korzekwa, Jaime Lorenzo-Trueba, Szymon Zaporowski +3
A common approach to the automatic detection of mispronunciation in language learning is to recognize the phonemes produced by a student and compare it to the expected pronunciatio…
EmoCat: Language-agnostic Emotional Voice Conversion
Bastian Schnell, Goeric Huybrechts, Bartek Perz +2
Emotional voice conversion models adapt the emotion in speech without changing the speaker identity or linguistic content. They are less data hungry than text-to-speech models and…
Detection of Lexical Stress Errors in Non-Native (L2) English with Data Augmentation and Attention
Daniel Korzekwa, Roberto Barra-Chicote, Szymon Zaporowski +6
This paper describes two novel complementary techniques that improve the detection of lexical stress errors in non-native (L2) English speech: attention-based feature extraction an…
Prosodic Representation Learning and Contextual Sampling for Neural Text-to-Speech
Sri Karlapati, Ammar Abbas, Zack Hodari +4
In this paper, we introduce Kathaka, a model trained with a novel two-stage training process for neural speech synthesis with contextually appropriate prosody. In Stage I, we learn…
CAMP: a Two-Stage Approach to Modelling Prosody in Context
Zack Hodari, Alexis Moinet, Sri Karlapati +6
Prosody is an integral part of communication, but remains an open problem in state-of-the-art speech synthesis. There are two major issues faced when modelling prosody: (1) prosody…
Parametric Representation for Singing Voice Synthesis: a Comparative Evaluation
Onur Babacan, Thomas Drugman, Tuomo Raitio +2
Various parametric representations have been proposed to model the speech signal. While the performance of such vocoders is well-known in the context of speech processing, their ex…
Maximum Phase Modeling for Sparse Linear Prediction of Speech
Thomas Drugman
Linear prediction (LP) is an ubiquitous analysis method in speech processing. Various studies have focused on sparse LP algorithms by introducing sparsity constraints into the LP f…
Analysis and Synthesis of Hypo and Hyperarticulated Speech
Benjamin Picart, Thomas Drugman, Thierry Dutoit
This paper focuses on the analysis and synthesis of hypo and hyperarticulated speech in the framework of HMM-based speech synthesis. First of all, a new French database matching ou…
Residual Excitation Skewness for Automatic Speech Polarity Detection
Thomas Drugman
Detecting the correct speech polarity is a necessary step prior to several speech processing techniques. An error on its determination could have a dramatic detrimental impact on t…
Maximum Voiced Frequency Estimation: Exploiting Amplitude and Phase Spectra
Thomas Drugman, Yannis Stylianou
Maximum Voiced Frequency (MVF) is used in various speech models as the spectral boundary separating periodic and aperiodic components during the production of voiced sounds. Recent…
Data-driven Detection and Analysis of the Patterns of Creaky Voice
Thomas Drugman, John Kane, Christer Gobl
This paper investigates the temporal excitation patterns of creaky voice. Creaky voice is a voice quality frequently used as a phrase-boundary marker, but also as a means of portra…