Papers with Code 아카이브
Audio Super-Resolution
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 4
- 보존된 평가 기록
- 14
Audio super-resolution, especially speech, refers to the process of reconstructing high-resolution music signals from their low-resolution counterparts. Essentially, it enhances the quality of a speech signal by increasing its sampling rate or bandwidth while preserving naturalness and intelligibility. A representative Github project for speech super-resolution is ClearerVoice-Studio.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
FLowHigh: Towards Efficient and High-Quality Audio Super-Resolution with Single-Step Flow Matching
AEROMamba: An efficient architecture for audio super-resolution using generative adversarial networks and state space models
Gull: A Generative Multifunctional Audio Codec
AudioSR: Versatile Audio Super-resolution at Scale
Edge Storage Management Recipe with Zero-Shot Data Compression for Road Anomaly Detection
AERO: Audio Super Resolution in the Spectral Domain
Nonparallel High-Quality Audio Super Resolution with Domain Adaptation and Resampling CycleGANs
CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement
NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates
Neural Vocoder is All You Need for Speech Super-resolution
Learning Continuous Representation of Audio for Arbitrary Scale Super Resolution
TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining
An investigation of pre-upsampling generative modelling and Generative Adversarial Networks in audio super resolution
Self-Attention for Audio Super-Resolution
NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling
On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks
Learning to Have an Ear for Face Super-Resolution
Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations
Audio Super Resolution using Neural Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.