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://bitbucket.org/rumschuettel/rvqe

공식 코드

Recurrent Quantum Neural Networks

https://github.com/0913ktg/sc_vall-e

공식 코드

SC VALL-E: Style-Controllable Zero-Shot Text to Speech Synthesizer

https://github.com/AI4Bharat/Rasa

공식 코드

Rasa: Building Expressive Speech Synthesis Systems for Indian Languages in Low-resource Settings

https://github.com/AmirmohammadRostami/KeywordsSpotting-EfficientNet-A0

공식 코드

EfficientNet-Absolute Zero for Continuous Speech Keyword Spotting

https://github.com/BME-SmartLab/DeepMOS

공식 코드

Improving Self-Supervised Learning-based MOS Prediction Networks

https://github.com/BME-SmartLab/txt-ult2wav

공식 코드

Speech Synthesis from Text and Ultrasound Tongue Image-based Articulatory Input

https://github.com/BME-SmartLab/txt2ult

공식 코드

Extending Text-to-Speech Synthesis with Articulatory Movement Prediction using Ultrasound Tongue Imaging

https://github.com/Berkeley-Speech-Group/PWVD-Pitch-Tracker

공식 코드

A Fast and Accurate Pitch Estimation Algorithm Based on the Pseudo Wigner-Ville Distribution

https://github.com/BogiHsu/Universal-Adaptor

공식 코드

Universal Adaptor: Converting Mel-Spectrograms Between Different Configurations for Speech Synthesis

https://github.com/CW-Huang/NAF

공식 코드

Neural Autoregressive Flows

https://github.com/Choddeok/EmoSphere-TTS

공식 코드

EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speech

https://github.com/Choddeok/EmoSpherepp

공식 코드

EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector

https://github.com/DeepGesture/DeepGesture-Unity

공식 코드

DeepGesture: A conversational gesture synthesis system based on emotions and semantics

https://github.com/Dekelv/ProsodicFeatureExtraction

공식 코드

Towards a Real-time Measure of the Perception of Anthropomorphism in Human-robot Interaction

https://github.com/ETZET/SpeechEmotionAVLearning

공식 코드

Learning Arousal-Valence Representation from Categorical Emotion Labels of Speech

https://github.com/Edresson/TTS-Portuguese-Corpus

공식 코드

TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese

https://github.com/Emotional-Text-to-Speech/dl-for-emo-tts

공식 코드

Exploring Transfer Learning for Low Resource Emotional TTS

https://github.com/HuSTeP-Human-Speech-Text-Processing-Lab/XLSR-GRKAN-Conformer

공식 코드

Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning Models

https://github.com/IS2AI/Kazakh_TTS

공식 코드

KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Dataset

https://github.com/Kyubyong/g2p

공식 코드

Learning pronunciation from a foreign language in speech synthesis networks

https://github.com/L0SG/NanoFlow

공식 코드

NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity

https://github.com/LIAvignon/adversarial-disentangling-autoencoder-for-spk-representation

공식 코드

Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation

https://github.com/MelissaChen15/control-vc

공식 코드

ControlVC: Zero-Shot Voice Conversion with Time-Varying Controls on Pitch and Speed

https://github.com/MingruiYuan/SpoofSV

공식 코드

Spoofing Speaker Verification Systems with Deep Multi-speaker Text-to-speech Synthesis

https://github.com/NVIDIA/NeMo

공식 코드

Adapter-Based Extension of Multi-Speaker Text-to-Speech Model for New Speakers

https://github.com/NVIDIA/OpenSeq2Seq

공식 코드

Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq

https://github.com/NVIDIA/flowtron

공식 코드

Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis

https://github.com/PaddlePaddle/PaddleSpeech

공식 코드

PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit

https://github.com/PaddlePaddle/Parakeet

공식 코드

WaveFlow: A Compact Flow-based Model for Raw Audio

https://github.com/Rongjiehuang/FastDiff

공식 코드

FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis

https://github.com/Rongjiehuang/GenerSpeech

공식 코드

GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech

https://github.com/Rongjiehuang/ProDiff

공식 코드

ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech

https://github.com/Rudrabha/Lip2Wav

공식 코드

Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis

https://github.com/ShangHua-Gao/RFNext

공식 코드

RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks

https://github.com/ShenranTomWang/TTS

공식 코드

Developing multilingual speech synthesis system for Ojibwe, Mi'kmaq, and Maliseet

https://github.com/SungFeng-Huang/Meta-TTS

공식 코드

Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speech

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