https://github.com/nvidia/bigvgan
공식 코드BigVGAN: A Universal Neural Vocoder with Large-Scale Training
Papers with Code 아카이브
Audio Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 4
- 평가표
- 3
- 보존된 평가 기록
- 26
Audio generation (synthesis) is the task of generating raw audio such as speech.
<span style="color:grey; opacity: 0.6">( Image credit: MelNet )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/nxtproduct/tunet
공식 코드https://github.com/open-mmlab/foleycrafter
공식 코드FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds
https://github.com/openai/sparse_attention
공식 코드https://github.com/qiuk2/aar
공식 코드Efficient Autoregressive Audio Modeling via Next-Scale Prediction
https://github.com/rastegah/kymatio-jtfs
공식 코드https://github.com/retrocirce/musicldm
공식 코드MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies
https://github.com/ristea/xmad-bench
공식 코드XMAD-Bench: Cross-Domain Multilingual Audio Deepfake Benchmark
https://github.com/ruizhecao96/cmgan
공식 코드CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement
https://github.com/see2sound/see2sound
공식 코드https://github.com/seongho608/ringformer
공식 코드RingFormer: A Neural Vocoder with Ring Attention and Convolution-Augmented Transformer
https://github.com/serkansulun/deep-music-enhancer
공식 코드On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks
https://github.com/sh01k/MeshRIR
공식 코드https://github.com/shaham-lab/disilv
공식 코드https://github.com/shlizee/Audeo
공식 코드https://github.com/slp-rl/aero
공식 코드https://github.com/soham97/adiff
공식 코드https://github.com/sony/soundctm
공식 코드SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation
https://github.com/soroushmehr/sampleRNN_ICLR2017
공식 코드SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
https://github.com/sp-uhh/sgmse
공식 코드https://github.com/sparkaudio/spark-tts
공식 코드Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens
https://github.com/spatialaudiotools/sofamyroom
공식 코드https://github.com/stability-ai/stable-audio-metrics
공식 코드https://github.com/stability-ai/stable-audio-tools
공식 코드https://github.com/stepfun-ai/step-audio
공식 코드Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction
https://github.com/symphonynet/SymphonyNet
공식 코드Symphony Generation with Permutation Invariant Language Model
https://github.com/theodorblackbird/lina-speech
공식 코드Small-E: Small Language Model with Linear Attention for Efficient Speech Synthesis
https://github.com/tifgan/stftGAN
공식 코드Adversarial Generation of Time-Frequency Features with application in audio synthesis
https://github.com/tobuta/PolyGlotFake
공식 코드PolyGlotFake: A Novel Multilingual and Multimodal DeepFake Dataset
https://github.com/tonychenxyz/emoknob
공식 코드EmoKnob: Enhance Voice Cloning with Fine-Grained Emotion Control
https://github.com/tpulkit/txt2vid
공식 코드Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text
https://github.com/usc-sail/synthaudio
공식 코드Can Synthetic Audio From Generative Foundation Models Assist Audio Recognition and Speech Modeling?
https://github.com/v-iashin/SpecVQGAN
공식 코드https://github.com/wguo86/ssv2a
공식 코드Gotta Hear Them All: Sound Source Aware Vision to Audio Generation
https://github.com/xieyuankun/Codecfake
공식 코드The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio
https://github.com/xieyuankun/all-type-add
공식 코드Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perception
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.