HIFI++: A Unified Framework for Bandwidth Extension and Speech Enhancement
Pavel Andreev, Aibek Alanov, Oleg V. Ivanov, Dmitry Vetrov
Abstract
Generative adversarial networks have recently demonstrated outstanding performance in neural vocoding outperforming best autoregressive and flow-based models. In this paper, we show that this success can be extended to other tasks of conditional audio generation. In particular, building upon HiFi vocoders, we propose a novel HiFi++ general frame-work for bandwidth extension and speech enhancement. We show that with the improved generator architecture, HiFi++ performs better or comparably with the state-of-the-art in these tasks while spending significantly less computational resources. The effectiveness of our approach is validated through a series of extensive experiments.
Topics & Concepts
Computer scienceBandwidth extensionExtension (predicate logic)Bandwidth (computing)Generator (circuit theory)Generative grammarAutoregressive modelSpeech recognitionArtificial intelligenceSpeech codingAudio signalTelecommunicationsProgramming languageMathematicsPower (physics)EconometricsQuantum mechanicsPhysicsSpeech and Audio ProcessingMusic and Audio ProcessingSpeech Recognition and Synthesis