Paper Archive

Recent diffusion-based generative models have achieved strong results in domain-specific audio generation tasks such as speech, singing, and instrumental music synthesis. However, these models are typically specialized and do not generalize well to mixed or intermediate audio types. In this work, we adapt a diffusion-based model originally designed for multi-instrument music synthesis to voice conversion, covering both speech and singing within a unified framework. Specifically, we extend musical note-based conditioning to include phonetic posteriorgrams (PPGs) and pitch contours, and reinterpret timbre conditioning as speaker or singer identity via feature-wise linear modulation. Experiments show that the adapted model matches or surpasses a dedicated voice conversion system in terms of naturalness and performer similarity, while maintaining accurate pitch control across speech and singing. At the same time, we observe limitations in phonetic fidelity and a degradation in vocal quality when incorporating instrumental training data. Furthermore, we demonstrate that off-the-shelf feature extractors provide effective conditioning signals, enabling large-scale self-supervised training without manual annotations. These results highlight the potential of cross-domain model transfer towards unified audio generation systems capable of handling speech, singing, and music.

Download

This work analyzes CLAP audio embeddings through a probing framework, studying the encoding of reverberation (RT60), loudness (LUFS), spectral content (SC), and relative pitch (RP). Results show that all attributes are reliably recoverable from CLAP embeddings, with RT60, LUFS, and RP approximately linearly encoded, while SC requires non-linear probes. The identified patterns generalize across eight additional audio foundation models.

Download

IRCAM has a long experience in analysis, synthesis and transformation of voice. Natural voice transformations are of great interest for many applications and can be combine with text-to-speech system, leading to a powerful creation tool. We present research conducted at IRCAM on voice transformations for the last few years. Transformations can be achieved in a global way by modifying pitch, spectral envelope, durations etc. While it sacrifices the possibility to attain a specific target voice, the approach allows the production of new voices of a high degree of naturalness with different gender and age, modified vocal quality, or another speech style. These transformations can be applied in realtime using ircamTools TR A X.Transformation can also be done in a more specific way in order to transform a voice towards the voice of a target speaker. Finally, we present some recent research on the transformation of expressivity.

Download

The 1st DAFx Parameter Estimation Challenge is an open initiative to advance the state of the art in parameter estimation for acoustic modeling. Stated as a system identification problem, this first edition focuses on plate reverberation—an archetypal dense, modal and weakly damped acoustic system. Participants tackled two tasks: (A) estimating the physical parameters of a vibrating plate from its impulse response, and (B) recovering the modal parameters of the same system. Both rest on a simulation framework based on the damped Kirchhoff–Love plate equation, and both are posed and scored entirely on synthetic data produced by that framework: no measurement of a real plate is involved. Two participants solved Task A down to machine precision by different strategies: one a neural network trained on a very large dataset, and one gradient-free optimization with many inexpensive evaluations. Task B proved considerably harder: the best submission attains a relative error of 0.33 on a [0, 2] scale, and every method recovers modal frequencies and decay rates far more accurately than modal gains. A complementary frequency-domain evaluation reorders the ranking and exposes a systematic gain bias to which the per-mode metric is blind.

Download