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/imxtx/awesome-controllabe-speech-synthesis

공식 코드

Towards Controllable Speech Synthesis in the Era of Large Language Models: A Survey

https://github.com/is2ai/kazemotts

공식 코드

KazEmoTTS: A Dataset for Kazakh Emotional Text-to-Speech Synthesis

https://github.com/is2ai/turkictts

공식 코드

Multilingual Text-to-Speech Synthesis for Turkic Languages Using Transliteration

https://github.com/janvainer/speedyspeech

공식 코드

SpeedySpeech: Efficient Neural Speech Synthesis

https://github.com/jik876/hifi-gan

공식 코드

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

https://github.com/jishengpeng/controlspeech

공식 코드

ControlSpeech: Towards Simultaneous and Independent Zero-shot Speaker Cloning and Zero-shot Language Style Control

https://github.com/joannahong/diffv2s

공식 코드

DiffV2S: Diffusion-based Video-to-Speech Synthesis with Vision-guided Speaker Embedding

https://github.com/jonaskohler/stereoeeg2speech

공식 코드

Synthesizing Speech from Intracranial Depth Electrodes using an Encoder-Decoder Framework

https://github.com/joseangl/transience

공식 코드

Multi-view Temporal Alignment for Non-parallel Articulatory-to-Acoustic Speech Synthesis

https://github.com/junjun3518/vifs

공식 코드

VIFS: An End-to-End Variational Inference for Foley Sound Synthesis

https://github.com/justinlovelace/sesd

공식 코드

Sample-Efficient Diffusion for Text-To-Speech Synthesis

https://github.com/jzq2000/mooncast

공식 코드

MoonCast: High-Quality Zero-Shot Podcast Generation

https://github.com/k2-fsa/ZipVoice

공식 코드

ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching

https://github.com/k2-fsa/icefall

공식 코드

Towards Universal Speech Discrete Tokens: A Case Study for ASR and TTS

https://github.com/kaistmm/voxsim_trainer

공식 코드

VoxSim: A perceptual voice similarity dataset

https://github.com/kakaobrain/jejueo

공식 코드

Jejueo Datasets for Machine Translation and Speech Synthesis

https://github.com/keonlee9420/STYLER

공식 코드

STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech

https://github.com/kexinhuang19/instructttseval

공식 코드

InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems

https://github.com/knoriy/emns-dct

공식 코드

EMNS /Imz/ Corpus: An emotive single-speaker dataset for narrative storytelling in games, television and graphic novels

https://github.com/komyeongjin/specdiff-gan

공식 코드

Adversarial Training of Denoising Diffusion Model Using Dual Discriminators for High-Fidelity Multi-Speaker TTS

https://github.com/kttrcdl/umetts

공식 코드

UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts

https://github.com/lee-jhwn/is25-emg-ema

공식 코드

Articulatory Feature Prediction from Surface EMG during Speech Production

https://github.com/litterbrother-xiao/overview-of-non-autoregressive-applications

공식 코드

A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond

https://github.com/liuxubo717/sound_generation

공식 코드

Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learning

https://github.com/ljuvela/ResGAN

공식 코드

Speech waveform synthesis from MFCC sequences with generative adversarial networks

https://github.com/ljuvela/collaborative-watermarking-with-codecs

공식 코드

Audio Codec Augmentation for Robust Collaborative Watermarking of Speech Synthesis

https://github.com/lorenlugosch/end-to-end-SLU

공식 코드

Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models

https://github.com/luotianze666/wavefm

공식 코드

WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matching

https://github.com/lwang114/unsuptts

공식 코드

Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition

https://github.com/lxchtan/omnidrca

공식 코드

OmniDRCA: Parallel Speech-Text Foundation Model via Dual-Resolution Speech Representations and Contrastive Alignment

https://github.com/mariganeshkumar/TDSNN-spoof-detection

공식 코드

Spoof detection using time-delay shallow neural network and feature switching

https://github.com/maxrmorrison/torbi

공식 코드

Fine-Grained and Interpretable Neural Speech Editing

https://github.com/mbinkowski/DeepSpeechDistances

공식 코드

High Fidelity Speech Synthesis with Adversarial Networks

https://github.com/mbzuai-nlp/artst

공식 코드

ArTST: Arabic Text and Speech Transformer

https://github.com/mbzuai-nlp/audiojailbreak

공식 코드

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models

https://github.com/mbzuai-nlp/sttatts

공식 코드

STTATTS: Unified Speech-To-Text And Text-To-Speech Model

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