Papers with Code 아카이브

Speech Synthesis

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/daisyqk/automatic-prosody-annotation

공식 코드

Automatic Prosody Annotation with Pre-Trained Text-Speech Model

https://github.com/dan8991/the-sound-of-silence

공식 코드

The Sound of Silence: Efficiency of First Digit Features in Synthetic Audio Detection

https://github.com/danielshaps/evoclearn_optccv_2022

공식 코드

Exploration strategies for articulatory synthesis of complex syllable onsets

https://github.com/dapwner/cvae-tacotron

공식 코드

Accented Text-to-Speech Synthesis with a Conditional Variational Autoencoder

https://github.com/declare-lab/adapter-mix

공식 코드

ADAPTERMIX: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptation

https://github.com/declare-lab/hypertts

공식 코드

HyperTTS: Parameter Efficient Adaptation in Text to Speech using Hypernetworks

https://github.com/declare-lab/speech-adapters

공식 코드

Evaluating Parameter-Efficient Transfer Learning Approaches on SURE Benchmark for Speech Understanding

https://github.com/deepvk/emospeech

공식 코드

EmoSpeech: Guiding FastSpeech2 Towards Emotional Text to Speech

https://github.com/descriptinc/melgan-neurips

공식 코드

MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis

https://github.com/dgaddy/silent_speech

공식 코드

Digital Voicing of Silent Speech

https://github.com/digitalphonetics/ims-toucan

공식 코드

Meta Learning Text-to-Speech Synthesis in over 7000 Languages

https://github.com/digitalphonetics/speaker-anonymization

공식 코드

Speaker Anonymization with Phonetic Intermediate Representations

https://github.com/dmse4tts/dmse4tts

공식 코드

Diffusion-Based Mel-Spectrogram Enhancement for Personalized Speech Synthesis with Found Data

https://github.com/edresson/wav2vec-wrapper

공식 코드

ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion

https://github.com/ehughson/voice_toolbox

공식 코드

Read the Room: Adapting a Robot's Voice to Ambient and Social Contexts

https://github.com/espnet/espnet

공식 코드

Towards Natural Bilingual and Code-Switched Speech Synthesis Based on Mix of Monolingual Recordings and Cross-Lingual Voice Conversion

https://github.com/facebookresearch/fairseq

공식 코드

Scaling Speech Technology to 1,000+ Languages

https://github.com/facebookresearch/seamless_communication

공식 코드

SeamlessM4T: Massively Multilingual & Multimodal Machine Translation

https://github.com/facebookresearch/vocoder-benchmark

공식 코드

VocBench: A Neural Vocoder Benchmark for Speech Synthesis

https://github.com/funaudiollm/cosyvoice

공식 코드

CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens

https://github.com/g-milis/NEUTART

공식 코드

Neural Text to Articulate Talk: Deep Text to Audiovisual Speech Synthesis achieving both Auditory and Photo-realism

https://github.com/gabrielmittag/NISQA

공식 코드

Deep Learning Based Assessment of Synthetic Speech Naturalness

https://github.com/gbegus/articulationgan

공식 코드

Articulation GAN: Unsupervised modeling of articulatory learning

https://github.com/gemelo-ai/vocos

공식 코드

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

https://github.com/gerazov/prosodeep

공식 코드

A Variational Prosody Model for the decomposition and synthesis of speech prosody

https://github.com/gokulkarthik/text2speech

공식 코드

Towards Building Text-To-Speech Systems for the Next Billion Users

https://github.com/google-research-datasets/common-crawl-domain-names

공식 코드

Semi-supervised URL Segmentation with Recurrent Neural NetworksPre-trained on Knowledge Graph Entities

https://github.com/google-research/google-research

공식 코드

A Spectral Energy Distance for Parallel Speech Synthesis

https://github.com/gpt-omni/mini-omni

공식 코드

Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming

https://github.com/hsoh0306/diffprosody

공식 코드

DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training

https://github.com/huawei-noah/Speech-Backbones

공식 코드

Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech

https://github.com/iamanigeeit/present

공식 코드

PRESENT: Zero-Shot Text-to-Prosody Control

https://github.com/ictnlp/llama-omni2

공식 코드

LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis

https://github.com/ictnlp/sled-tts

공식 코드

Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space

https://github.com/ictnlp/streamspeech

공식 코드

StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning

https://github.com/idiap/bayesian-peft

공식 코드

Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.