Litcius/Paper detail

Task Splitting for DNN-based Acoustic Echo and Noise Removal

Sebastian Braun, María Luis Valero

202216 citationsDOI

Abstract

Neural networks have led to tremendous performance gains for single-task speech enhancement, such as noise suppression and acoustic echo cancellation (AEC). In this work, we evaluate whether it is more useful to use a single joint or separate modules to tackle these problems. We describe different possible implementations and give insights into their performance and efficiency. We show that using a separate echo cancellation module and a module for noise and residual echo removal results in less near-end speech distortion and better performance during double-talk at same complexity.

Topics & Concepts

Echo (communications protocol)Computer scienceNoise (video)Task (project management)Speech recognitionDistortion (music)Speech enhancementImplementationResidualNoise reductionArtificial intelligenceAlgorithmTelecommunicationsEngineeringBandwidth (computing)Image (mathematics)Systems engineeringProgramming languageComputer networkAmplifierSpeech and Audio ProcessingAdvanced Adaptive Filtering TechniquesHearing Loss and Rehabilitation
Task Splitting for DNN-based Acoustic Echo and Noise Removal | Litcius