10 citations · 31 across the 20 of their papers we have counts for
24 papers
Universal Semantic Disentangled Privacy-preserving Speech Representation Learning
Biel Tura Vecino, Subhadeep Maji, Aravind Varier +11
The use of audio recordings of human speech to train LLMs poses privacy concerns due to these models' potential to generate outputs that closely resemble artifacts in the training…
Investigating self-supervised features for expressive, multilingual voice conversion
Álvaro Martín-Cortinas, Daniel Sáez-Trigueros, Grzegorz Beringer +7
Voice conversion (VC) systems are widely used for several applications, from speaker anonymisation to personalised speech synthesis. Supervised approaches learn a mapping between d…
Enhancing the Stability of LLM-based Speech Generation Systems through Self-Supervised Representations
Álvaro Martín-Cortinas, Daniel Sáez-Trigueros, Iván Vallés-Pérez +6
Large Language Models (LLMs) are one of the most promising technologies for the next era of speech generation systems, due to their scalability and in-context learning capabilities…
Creating New Voices using Normalizing Flows
Piotr Bilinski, Thomas Merritt, Abdelhamid Ezzerg +5
Creating realistic and natural-sounding synthetic speech remains a big challenge for voice identities unseen during training. As there is growing interest in synthesizing voices of…
Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speech
Guangyan Zhang, Thomas Merritt, Manuel Sam Ribeiro +10
Neural text-to-speech systems are often optimized on L1/L2 losses, which make strong assumptions about the distributions of the target data space. Aiming to improve those assumptio…
SCRAPS: Speech Contrastive Representations of Acoustic and Phonetic Spaces
Ivan Vallés-Pérez, Grzegorz Beringer, Piotr Bilinski +2
Numerous examples in the literature proved that deep learning models have the ability to work well with multimodal data. Recently, CLIP has enabled deep learning systems to learn s…
Remap, warp and attend: Non-parallel many-to-many accent conversion with Normalizing Flows
Abdelhamid Ezzerg, Thomas Merritt, Kayoko Yanagisawa +6
Regional accents of the same language affect not only how words are pronounced (i.e., phonetic content), but also impact prosodic aspects of speech such as speaking rate and intona…
Stutter-TTS: Controlled Synthesis and Improved Recognition of Stuttered Speech
Xin Zhang, Iván Vallés-Pérez, Andreas Stolcke +5
Stuttering is a speech disorder where the natural flow of speech is interrupted by blocks, repetitions or prolongations of syllables, words and phrases. The majority of existing au…
GlowVC: Mel-spectrogram space disentangling model for language-independent text-free voice conversion
Magdalena Proszewska, Grzegorz Beringer, Daniel Sáez-Trigueros +3
In this paper, we propose GlowVC: a multilingual multi-speaker flow-based model for language-independent text-free voice conversion. We build on Glow-TTS, which provides an archite…
Prosodic Alignment for off-screen automatic dubbing
Yogesh Virkar, Marcello Federico, Robert Enyedi +1
The goal of automatic dubbing is to perform speech-to-speech translation while achieving audiovisual coherence. This entails isochrony, i.e., translating the original speech by als…
Text-free non-parallel many-to-many voice conversion using normalising flows
Thomas Merritt, Abdelhamid Ezzerg, Piotr Biliński +4
Non-parallel voice conversion (VC) is typically achieved using lossy representations of the source speech. However, ensuring only speaker identity information is dropped whilst all…
Voice Filter: Few-shot text-to-speech speaker adaptation using voice conversion as a post-processing module
Adam Gabryś, Goeric Huybrechts, Manuel Sam Ribeiro +6
State-of-the-art text-to-speech (TTS) systems require several hours of recorded speech data to generate high-quality synthetic speech. When using reduced amounts of training data,…
Improving the expressiveness of neural vocoding with non-affine Normalizing Flows
Adam Gabryś, Yunlong Jiao, Viacheslav Klimkov +2
This paper proposes a general enhancement to the Normalizing Flows (NF) used in neural vocoding. As a case study, we improve expressive speech vocoding with a revamped Parallel Wav…
SynthASR: Unlocking Synthetic Data for Speech Recognition
Amin Fazel, Wei Yang, Yulan Liu +4
End-to-end (E2E) automatic speech recognition (ASR) models have recently demonstrated superior performance over the traditional hybrid ASR models. Training an E2E ASR model require…
Improving multi-speaker TTS prosody variance with a residual encoder and normalizing flows
Iván Vallés-Pérez, Julian Roth, Grzegorz Beringer +2
Text-to-speech systems recently achieved almost indistinguishable quality from human speech. However, the prosody of those systems is generally flatter than natural speech, produci…
Parallel WaveNet conditioned on VAE latent vectors
Jonas Rohnke, Tom Merritt, Jaime Lorenzo-Trueba +4
Recently the state-of-the-art text-to-speech synthesis systems have shifted to a two-model approach: a sequence-to-sequence model to predict a representation of speech (typically m…
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…
BOFFIN TTS: Few-Shot Speaker Adaptation by Bayesian Optimization
Henry B. Moss, Vatsal Aggarwal, Nishant Prateek +2
We present BOFFIN TTS (Bayesian Optimization For FIne-tuning Neural Text To Speech), a novel approach for few-shot speaker adaptation. Here, the task is to fine-tune a pre-trained…
From Speech-to-Speech Translation to Automatic Dubbing
Marcello Federico, Robert Enyedi, Roberto Barra-Chicote +4
We present enhancements to a speech-to-speech translation pipeline in order to perform automatic dubbing. Our architecture features neural machine translation generating output of…
Using VAEs and Normalizing Flows for One-shot Text-To-Speech Synthesis of Expressive Speech
Vatsal Aggarwal, Marius Cotescu, Nishant Prateek +2
We propose a Text-to-Speech method to create an unseen expressive style using one utterance of expressive speech of around one second. Specifically, we enhance the disentanglement…
Interpretable Deep Learning Model for the Detection and Reconstruction of Dysarthric Speech
Daniel Korzekwa, Roberto Barra-Chicote, Bozena Kostek +2
This paper proposed a novel approach for the detection and reconstruction of dysarthric speech. The encoder-decoder model factorizes speech into a low-dimensional latent space and…
In Other News: A Bi-style Text-to-speech Model for Synthesizing Newscaster Voice with Limited Data
Nishant Prateek, Mateusz Łajszczak, Roberto Barra-Chicote +5
Neural text-to-speech synthesis (NTTS) models have shown significant progress in generating high-quality speech, however they require a large quantity of training data. This makes…
Comprehensive evaluation of statistical speech waveform synthesis
Thomas Merritt, Bartosz Putrycz, Adam Nadolski +10
Statistical TTS systems that directly predict the speech waveform have recently reported improvements in synthesis quality. This investigation evaluates Amazon's statistical speech…
Towards achieving robust universal neural vocoding
Jaime Lorenzo-Trueba, Thomas Drugman, Javier Latorre +5
This paper explores the potential universality of neural vocoders. We train a WaveRNN-based vocoder on 74 speakers coming from 17 languages. This vocoder is shown to be capable of…