Audio Enhancement for Computer Audition -- An Iterative Training Paradigm Using Sample Importance
Milling, Manuel, Liu, Shuo, Triantafyllopoulos, Andreas, Aslan, Ilhan, Schuller, Björn W.
–arXiv.org Artificial Intelligence
Neural network models for audio tasks, such as automatic speech recognition (ASR) and acoustic scene classification (ASC), are susceptible to noise contamination for real-life applications. To improve audio quality, an enhancement module, which can be developed independently, is explicitly used at the front-end of the target audio applications. In this paper, we present an end-to-end learning solution to jointly optimise the models for audio enhancement (AE) and the subsequent applications. To guide the optimisation of the AE module towards a target application, and especially to overcome difficult samples, we make use of the sample-wise performance measure as an indication of sample importance. In experiments, we consider four representative applications to evaluate our training paradigm, i.e., ASR, speech command recognition (SCR), speech emotion recognition (SER), and ASC. These applications are associated with speech and non-speech tasks concerning semantic and non-semantic features, transient and global information, and the experimental results indicate that our proposed approach can considerably boost the noise robustness of the models, especially at low signal-to-noise ratios (SNRs), for a wide range of computer audition tasks in everyday-life noisy environments.
arXiv.org Artificial Intelligence
Aug-12-2024
- Country:
- South America > Chile
- Oceania > Australia
- Queensland > Brisbane (0.04)
- North America
- United States
- Pennsylvania > Allegheny County
- Pittsburgh (0.04)
- New York > New York County
- New York City (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- California > Santa Clara County
- Sunnyvale (0.04)
- Pennsylvania > Allegheny County
- Canada
- Quebec > Montreal (0.04)
- Ontario > Toronto (0.04)
- Alberta (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.04)
- United States
- Europe
- Austria
- Germany
- Saxony > Dresden (0.04)
- Saarland (0.04)
- Hesse > Darmstadt Region
- Darmstadt (0.04)
- Bavaria > Upper Bavaria
- Munich (0.05)
- Greece > West Greece
- Patra (0.04)
- United Kingdom > England
- Greater London > London (0.04)
- East Sussex > Brighton (0.04)
- Czechia > Liberec Region
- Liberec (0.04)
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- Italy > Calabria
- Catanzaro Province > Catanzaro (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Portugal > Coimbra
- Coimbra (0.04)
- Asia
- Singapore (0.04)
- Japan > Honshū
- Kantō > Tokyo Metropolis Prefecture > Tokyo (0.14)
- China
- Shanghai > Shanghai (0.04)
- Shandong Province (0.04)
- Jiangsu Province > Nanjing (0.04)
- Genre:
- Research Report (1.00)
- Industry:
- Education (0.69)
- Information Technology (0.67)
- Health & Medicine > Therapeutic Area (0.46)
- Technology: