405 citations · 659 across the 15 of their papers we have counts for
16 papers
On Information Geometry and Iterative Optimization in Model Compression: Operator Factorization
Zakhar Shumaylov, Vasileios Tsiaras, Yannis Stylianou
The ever-increasing parameter counts of deep learning models necessitate effective compression techniques for deployment on resource-constrained devices. This paper explores the ap…
Vocal effort modeling in neural TTS for improving the intelligibility of synthetic speech in noise
Tuomo Raitio, Petko Petkov, Jiangchuan Li +3
We present a neural text-to-speech (TTS) method that models natural vocal effort variation to improve the intelligibility of synthetic speech in the presence of noise. The method c…
Combining speakers of multiple languages to improve quality of neural voices
Javier Latorre, Charlotte Bailleul, Tuuli Morrill +2
In this work, we explore multiple architectures and training procedures for developing a multi-speaker and multi-lingual neural TTS system with the goals of a) improving the qualit…
Evaluating the Intelligibility Benefits of Neural Speech Enrichment for Listeners with Normal Hearing and Hearing Impairment using the Greek Harvard Corpus
Muhammed PV Shifas, Anna Sfakianaki, Theognosia Chimona +1
In this work we evaluate a neural based speech intelligibility booster based on spectral shaping and dynamic range compression (SSDRC), referred to as WaveNet-based SSDRC (wSSDRC),…
Enhancing Speech Intelligibility in Text-To-Speech Synthesis using Speaking Style Conversion
Dipjyoti Paul, Muhammed PV Shifas, Yannis Pantazis +1
The increased adoption of digital assistants makes text-to-speech (TTS) synthesis systems an indispensable feature of modern mobile devices. It is hence desirable to build a system…
Speaker Conditional WaveRNN: Towards Universal Neural Vocoder for Unseen Speaker and Recording Conditions
Dipjyoti Paul, Yannis Pantazis, Yannis Stylianou
Recent advancements in deep learning led to human-level performance in single-speaker speech synthesis. However, there are still limitations in terms of speech quality when general…
Audiovisual Speech Synthesis using Tacotron2
Ahmed Hussen Abdelaziz, Anushree Prasanna Kumar, Chloe Seivwright +4
Audiovisual speech synthesis is the problem of synthesizing a talking face while maximizing the coherency of the acoustic and visual speech. In this paper, we propose and compare t…
A non-causal FFTNet architecture for speech enhancement
Muhammed PV Shifas, Nagaraj Adiga, Vassilis Tsiaras +1
In this paper, we suggest a new parallel, non-causal and shallow waveform domain architecture for speech enhancement based on FFTNet, a neural network for generating high quality a…
Cumulant GAN
Yannis Pantazis, Dipjyoti Paul, Michail Fasoulakis +2
In this paper, we propose a novel loss function for training Generative Adversarial Networks (GANs) aiming towards deeper theoretical understanding as well as improved stability an…
A fully recurrent feature extraction for single channel speech enhancement
Muhammed PV Shifas, Santelli Claudio, Vassilis Tsiaras +1
Convolutional neural network (CNN) modules are widely being used to build high-end speech enhancement neural models. However, the feature extraction power of vanilla CNN modules ha…
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…
Voice Activity Detection: Merging Source and Filter-based Information
Thomas Drugman, Yannis Stylianou, Yusuke Kida +1
Voice Activity Detection (VAD) refers to the problem of distinguishing speech segments from background noise. Numerous approaches have been proposed for this purpose. Some are base…
Training Generative Adversarial Networks with Weights
Yannis Pantazis, Dipjyoti Paul, Michail Fasoulakis +1
The impressive success of Generative Adversarial Networks (GANs) is often overshadowed by the difficulties in their training. Despite the continuous efforts and improvements, there…
Automatic acoustic detection of birds through deep learning: the first Bird Audio Detection challenge
Dan Stowell, Yannis Stylianou, Mike Wood +2
Assessing the presence and abundance of birds is important for monitoring specific species as well as overall ecosystem health. Many birds are most readily detected by their sounds…
LD-SDS: Towards an Expressive Spoken Dialogue System based on Linked-Data
Alexandros Papangelis, Panagiotis Papadakos, Margarita Kotti +3
In this work we discuss the related challenges and describe an approach towards the fusion of state-of-the-art technologies from the Spoken Dialogue Systems (SDS) and the Semantic…
Bird detection in audio: a survey and a challenge
Dan Stowell, Mike Wood, Yannis Stylianou +1
Many biological monitoring projects rely on acoustic detection of birds. Despite increasingly large datasets, this detection is often manual or semi-automatic, requiring manual tun…