Michelle Mao — accepted AI-conference papers

2024

Low Bitrate Loss Resilience Scheme for a Speech Enhancing Neural Codec

Mihailo Kolundzija, Mathew Shaji Kavalekalam, Ivana Balic, Michelle Mao, Raúl Casas

ICASSP 2024accepted

Deep neural networks have proven their efficacy in encoding high-quality speech and audio at remarkably low bitrates, while also demonstrating superior performance in audio packet loss concealment (PLC) compared to traditional methods. Although ultra low-bitrate speech and audio codecs may appear le…

Cited by 0 Source ↗Scholar ↗

2024

SECP: A Speech Enhancement-Based Curation Pipeline for Scalable Acquisition of Clean Speech

Adam Sabra, Cyprian M. Wronka, Michelle Mao, Samer L. Hijazi

ICASSP 2024accepted

As more speech technologies rely on a supervised deep learning approach with clean speech as the ground truth, a methodology to onboard said speech at scale is needed. However, this approach needs to minimize the dependency on human listening and annotation, only requiring a human-in-the-loop when n…

Cited by 0 Source ↗Scholar ↗