Nicola Pia

Fraunhofer Institute for Integrated Circuits — Germany

Computer Science · Physical Sciences

4h-index76citations31works0.52yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech Recognition and Synthesis(14), Speech and Audio Processing(13), Advanced Data Compression Techniques(8), Geometry and complex manifolds(6), Neural Networks and Applications(5)

Publications31 total

UBGAN: Enhancing Coded Speech with Blind and Guided Bandwidth Extension
2025Open Access
Bridging the Training–Inference Gap in TTS: Training Strategies for Robust Generative Postprocessing for Low-Resource Speakers
2025
UBGAN: Enhancing Coded Speech with Blind and Guided Bandwidth Extension
arXiv (Cornell University)·2025Open Access
FlowMAC: Conditional Flow Matching for Audio Coding at Low Bit Rates
2025
Low-Resource Text-to-Speech Synthesis Using Noise-Augmented Training of ForwardTacotron
2025· 2 cited
Low-Resource Text-to-Speech Synthesis Using Noise-Augmented Training of ForwardTacotron
arXiv (Cornell University)·2025Open Access
Neural Speech Coding for Real-Time Communications Using Constant Bitrate Scalar Quantization
IEEE Journal of Selected Topics in Signal Processing·2024· 3 cited
FlowMAC: Conditional Flow Matching for Audio Coding at Low Bit Rates
arXiv (Cornell University)·2024Open Access
On Improving Error Resilience of Neural End-to-End Speech Coders
2024
On Improving Error Resilience of Neural End-to-End Speech Coders
arXiv (Cornell University)·2024Open Access
Neural Speech Coding for Real-time Communications using Constant Bitrate Scalar Quantization
arXiv (Cornell University)·2024Open Access
SEFGAN: Harvesting the Power of Normalizing Flows and GANs for Efficient High-Quality Speech Enhancement
2023· 4 citedOpen Access
Low-Resource Text-to-Speech Using Specific Data and Noise Augmentation
2023· 3 cited
Subjective Evaluation of Text-to-Speech Models: Comparing Absolute Category Rating and Ranking by Elimination Tests
2023· 1 cited
Low-Resource Text-to-Speech Using Specific Data and Noise Augmentation
arXiv (Cornell University)·2023· 2 citedOpen Access
NESC: Robust Neural End-2-End Speech Coding with GANs
Interspeech 2022·2022· 14 cited
NESC: Robust Neural End-2-End Speech Coding with GANs
arXiv (Cornell University)·2022Open Access
PostGAN: A GAN-Based Post-Processor to Enhance the Quality of Coded Speech
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)·2022· 18 cited
PostGAN: A GAN-Based Post-Processor to Enhance the Quality of Coded Speech
arXiv (Cornell University)·2022Open Access
A Streamwise Gan Vocoder for Wideband Speech Coding at Very Low Bit Rate
2021· 18 cited
page 1 of 2Next →

Frequent Co-authors

Guillaume Fuchs(14), Srikanth Korse(10), Markus Multrus(8), Kishan Chand Gupta(6), Kishor Kayyar Lakshminarayana(6), Christian Dittmar(6), Emanuël A. P. Habets(6), Andreas Brendel(6), Kishan Gupta(5), Bernd Edler(3), Frank Zalkow(3), Ahmed Mustafa(2), Jan Büthe(2), R.M.F. Coelho(2), Ahmed Mustafa(2), Giovanni Placini(2), Martin J. Strauss(2), M. Strauss(1), Nagashree K. S. Rao(1), Lyonel Behringer(1)