Papers with Code 아카이브
Speech Synthesis
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 15
- 평가표
- 5
- 보존된 평가 기록
- 31
Speech synthesis is the task of generating speech from some other modality like text, lip movements etc.
Please note that the leaderboards here are not really comparable between studies - as they use mean opinion score as a metric and collect different samples from Amazon Mechnical Turk.
<span style="color:grey; opacity: 0.6">( Image credit: WaveNet: A generative model for raw audio )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/ivanvovk/DurIAN
DurIAN: Duration Informed Attention Network For Multimodal Synthesis
https://github.com/ivanvovk/WaveGrad
https://github.com/ivanvovk/durian-pytorch
DurIAN: Duration Informed Attention Network For Multimodal Synthesis
https://github.com/izzajalandoni/tts_models
https://github.com/jackaduma/CycleGAN-VC2
https://github.com/jackson-kang/vqvc-pytorch
VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Network
https://github.com/jacksonkaunismaa/neural-music
MelNet: A Generative Model for Audio in the Frequency Domain
https://github.com/jasminsternkopf/mel_cepstral_distance
Effective Use of Variational Embedding Capacity in Expressive End-to-End Speech Synthesis
https://github.com/jaywalnut310/glow-tts
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
https://github.com/jaywalnut310/melgan-pytorch
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
https://github.com/jessearodriguez/LJ-Audio-dataset-generator
https://github.com/jiean001/models_m/tree/main/tacotron2
Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
https://github.com/jinhan/tacotron2-gst
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
https://github.com/jinhan/tacotron2-vae
Learning latent representations for style control and transfer in end-to-end speech synthesis
https://github.com/jkyunnng/happyquokka_system_for_eeg_challenge
https://github.com/joannahong/lip-to-speech-synthesis-in-the-wild
Lip-to-Speech Synthesis in the Wild with Multi-task Learning
https://github.com/junwang23/deepdirtycodes
A Critical Review of Recurrent Neural Networks for Sequence Learning
https://github.com/kaiidams/voice100
Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning
https://github.com/kaiidams/voice100-tts
Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning
https://github.com/kaistmm/v2sflow
https://github.com/karpathy/makemore
https://github.com/kdaip/stabletts
https://github.com/keithito/tacotron
https://github.com/kensun0/Parallel-Wavenet
ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech
https://github.com/keonlee9420/Comprehensive-E2E-TTS
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/keonlee9420/Comprehensive-Tacotron2
https://github.com/keonlee9420/Comprehensive-Transformer-TTS
https://github.com/keonlee9420/Cross-Speaker-Emotion-Transfer
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
https://github.com/keonlee9420/DailyTalk
https://github.com/keonlee9420/DiffGAN-TTS
Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
https://github.com/keonlee9420/DiffSinger
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/keonlee9420/Expressive-FastSpeech2
https://github.com/keonlee9420/FastPitchFormant
FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis
https://github.com/keonlee9420/PortaSpeech
https://github.com/keonlee9420/Robust_Fine_Grained_Prosody_Control
Robust and fine-grained prosody control of end-to-end speech synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.