4 papers
Beyond Cross-Reconstruction: Probing-Based Disentanglement Evaluation for Acoustic Teleportation Codecs
Philipp Grundhuber, Emanuël A. P. Habets
Some neural audio codecs disentangle speech into latent subspaces encoding content, speaker identity, and acoustics, enabling acoustic teleportation and voice conversion. Existing…
Robust Speech Activity Detection in the Presence of Singing Voice
Philipp Grundhuber, Mhd Modar Halimeh, Martin Strauà +1
Speech Activity Detection (SAD) systems often misclassify singing as speech, leading to degraded performance in applications such as dialogue enhancement and automatic speech recog…
Acoustic Teleportation via Disentangled Neural Audio Codec Representations
Philipp Grundhuber, Mhd Modar Halimeh, Emanuël A. P. Habets
This paper presents an approach for acoustic teleportation by disentangling speech content from acoustic environment characteristics in neural audio codec representations. Acoustic…
On the Relation Between Speech Quality and Quantized Latent Representations of Neural Codecs
Mhd Modar Halimeh, Matteo Torcoli, Philipp Grundhuber +1
Neural audio signal codecs have attracted significant attention in recent years. In essence, the impressive low bitrate achieved by such encoders is enabled by learning an abstract…