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/popcornell/ASRLightningFT

공식 코드

Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition

https://github.com/potamitis123/chatgpt-in-the-context-of-precision-agriculture-data-analytics

공식 코드

ChatGPT in the context of precision agriculture data analytics

https://github.com/pussycat0700/divise

공식 코드

DiVISe: Direct Visual-Input Speech Synthesis Preserving Speaker Characteristics And Intelligibility

https://github.com/pytorch/fairseq

공식 코드

fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit

https://github.com/rainbowluocs/openomni

공식 코드

OpenOmni: Large Language Models Pivot Zero-shot Omnimodal Alignment across Language with Real-time Self-Aware Emotional Speech Synthesis

https://github.com/redmist328/apnet2

공식 코드

APNet2: High-quality and High-efficiency Neural Vocoder with Direct Prediction of Amplitude and Phase Spectra

https://github.com/rf5/simple-asgan

공식 코드

GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models

https://github.com/rhoposit/icassp2021

공식 코드

Learning Disentangled Phone and Speaker Representations in a Semi-Supervised VQ-VAE Paradigm

https://github.com/roblox/smoothcache

공식 코드

SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers

https://github.com/rohan-chaudhury/humane-speech-synthesis-through-zero-shot-emotion-and-disfluency-generation

공식 코드

Humane Speech Synthesis through Zero-Shot Emotion and Disfluency Generation

https://github.com/roholazandie/ryan-tts

공식 코드

RyanSpeech: A Corpus for Conversational Text-to-Speech Synthesis

https://github.com/samsad35/code-ancogen

공식 코드

AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder

https://github.com/sarulab-speech/saslaw

공식 코드

SaSLaW: Dialogue Speech Corpus with Audio-visual Egocentric Information Toward Environment-adaptive Dialogue Speech Synthesis

https://github.com/scarletcho/KoG2P

공식 코드

Learning pronunciation from a foreign language in speech synthesis networks

https://github.com/sh-lee-prml/hierspeechpp

공식 코드

HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis

https://github.com/sh-lee-prml/periodwave

공식 코드

PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation

https://github.com/shark-nlp/attentivemlp

공식 코드

Attentive Multi-Layer Perceptron for Non-autoregressive Generation

https://github.com/shinhyeokoh/rwen

공식 코드

RWEN-TTS: Relation-aware Word Encoding Network for Natural Text-to-Speech Synthesis

https://github.com/shivammehta25/Matcha-TTS

공식 코드

Matcha-TTS: A fast TTS architecture with conditional flow matching

https://github.com/shivammehta25/Neural-HMM

공식 코드

Neural HMMs are all you need (for high-quality attention-free TTS)

https://github.com/shivammehta25/OverFlow

공식 코드

OverFlow: Putting flows on top of neural transducers for better TTS

https://github.com/sivannavis/samo

공식 코드

SAMO: Speaker Attractor Multi-Center One-Class Learning for Voice Anti-Spoofing

https://github.com/smileslab/comparative-analysis-voice-spoofing

공식 코드

Voice Spoofing Countermeasures: Taxonomy, State-of-the-art, experimental analysis of generalizability, open challenges, and the way forward

https://github.com/sony/bigvsan

공식 코드

BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network

https://github.com/sony/bigvsan_eval

공식 코드

BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network

https://github.com/soroushmehr/sampleRNN_ICLR2017

공식 코드

SampleRNN: An Unconditional End-to-End Neural Audio Generation Model

https://github.com/sp-nitech/diffsptk

공식 코드

Embedding a Differentiable Mel-cepstral Synthesis Filter to a Neural Speech Synthesis System

https://github.com/speechbrain/speechbrain

공식 코드

SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation

https://github.com/ssmlkl/mntts2

공식 코드

MnTTS2: An Open-Source Multi-Speaker Mongolian Text-to-Speech Synthesis Dataset

https://github.com/stt4sg/dialektsammlung-public

공식 코드

SDS-200: A Swiss German Speech to Standard German Text Corpus

https://github.com/tencent-ailab/bddm

공식 코드

BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis

https://github.com/theodorblackbird/lina-speech

공식 코드

Small-E: Small Language Model with Linear Attention for Efficient Speech Synthesis

https://github.com/thuhcsi/speechcraft

공식 코드

SpeechCraft: A Fine-grained Expressive Speech Dataset with Natural Language Description

https://github.com/tiberiu44/TTS-Cube

공식 코드

Generative Adversarial Training for Text-to-Speech Synthesis Based on Raw Phonetic Input and Explicit Prosody Modelling

https://github.com/tonychenxyz/emoknob

공식 코드

EmoKnob: Enhance Voice Cloning with Fine-Grained Emotion Control

https://github.com/tts-tutorial/survey

공식 코드

A Survey on Neural Speech Synthesis

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