Litcius/Paper detail

TSpeech-AI System Description to the 5th Deep Noise Suppression (DNS) Challenge

Jianwei Yu, Hangting Chen, Yi Luo, Rongzhi Gu, Weihua Li, Chao Weng

202310 citationsDOI

Abstract

This report presents the development of Tencent AI Lab’s personalized speech enhancement system for the 2023 ICASSP Signal Processing Grand Challenge – deep noise suppression (DNS) challenge <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> , which includes the use of a modified band-split recurrent neural network (BSRNN) and a multi-resolution spectrogram discriminator to improve perceptual quality metrics. The proposed system outperforms the baseline system by 0.047 and 0.036 final scores in the headset track and speaker phone track, respectively, and ranks among the top-3 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> in both tracks.

Topics & Concepts

HeadsetSpectrogramNoise (video)Computer scienceSpeech recognitionRaspberry piArtificial intelligencePhoneSIGNAL (programming language)Track (disk drive)Signal processingTelecommunicationsWorld Wide WebDigital signal processingInternet of ThingsProgramming languageComputer hardwareOperating systemImage (mathematics)LinguisticsPhilosophySpeech Recognition and SynthesisSpeech and Audio ProcessingMusic and Audio Processing
TSpeech-AI System Description to the 5th Deep Noise Suppression (DNS) Challenge | Litcius