2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
| Paper ID | AUD-17.1 | ||
| Paper Title | ACOUSTIC REFLECTORS LOCALIZATION FROM STEREO RECORDINGS USING NEURAL NETWORKS | ||
| Authors | Giovanni Bologni, Richard Heusdens, Jorge Martinez, Technical University of Delft, Netherlands | ||
| Session | AUD-17: Modeling, Analysis and Synthesis of Acoustic Environments 3: Acoustic Analysis | ||
| Location | Gather.Town | ||
| Session Time: | Wednesday, 09 June, 16:30 - 17:15 | ||
| Presentation Time: | Wednesday, 09 June, 16:30 - 17:15 | ||
| Presentation | Poster | ||
| Topic | Audio and Acoustic Signal Processing: [AUD-MAAE] Modeling, Analysis and Synthesis of Acoustic Environments | ||
| IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
| Abstract | Acoustic room geometry estimation is often performed in ad hoc settings, i.e. using multiple microphones and sources distributed around the room, or assuming control over the excitation signals. We propose a fully convolutional network (FCN) that localizes reflective surfaces under the relaxed assumptions that (i) a compact array of only two microphones is available, (ii) emitter and receivers are not synchronized, and (iii) both the excitation signals and the impulse responses of the enclosures are unknown. Our FCN is trained in a supervised fashion to predict the likelihood of sources at specific distances and directions-of-arrival (DOA). When a single reflective surface is present, up to 80% of real and virtual sources are detected, while this figure approaches 50% in rectangular rooms. Experiments on real-world recordings report similar accuracy as with artificially reverberated speech signals, validating the generalization capabilities of the framework. | ||