[Paper Review] Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech
사람의 얼굴에 어울리는 목소리를 자동으로 만들어주는 디퓨전 기반 TTS 모델
Posts by Tag
- Speech Synthesis 33
- TTS 23
- G2P 8
- Time Series 5
- Transformer 5
- GAN 5
- Neural Codec Language Model 4
- Custom Voice 3
- MOS 3
- Zero-Shot 3
- ASR 2
- Survey 2
- Finance 2
- Stock Price Prediction 2
- Vocoder 2
- Flow 2
- VAE 2
- Style Embedding 2
- LSTM 2
- Speaker Generation 2
- Audio Compression 2
- Codec 2
- Anti Spoofing 2
- Audio Deepfake Detection 2
- Speech Processing 1
- SR 1
- SER 1
- Financial Engineering 1
- Loss Function 1
- Dynamic Time Warping 1
- Long Sequence 1
- Audio Synthesis 1
- Neural Vocoder 1
- Meta Learning 1
- Multi Speaker 1
- Seq2Seq 1
- BERT 1
- Byte representation 1
- Lexicon 1
- Speech Recognition 1
- Contrastive Learning 1
- Diffusion 1
- Prompt TTS 1
- Natural Language Guidance 1
- Duration 1
- Flow Matching 1
- Spontaneous Speech 1
- Cross-Lingual TTS 1
- Speech-to-Speech 1
- Code Switching 1
- GNN 1
- AI Agent 1
- Hugging Face 1
- LLM 1
- Online Course 1
- Audio Augmentation 1
Speech Synthesis
[Paper Review] VoiceMe: Personalized voice generation in TTS
인물의 사진을 보고 어울리는 음성을 직접 제작할 수 있는 모델
[Paper Review] NN-KOG2P: A Novel Grapheme-To-Phoneme Model for Korean Language
한국어의 발음특성을 고려한 FFNN G2P 모델
[Paper Review] Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
Diffusion Probabilistic Model 기반 decoder를 사용한 TTS 모델
[Paper Review] Label Embedding for Chinese Grapheme-to-Phoneme Conversion
contrastive learning을 활용한 중국어 G2P
[Paper Review] Almost Unsupervised Text to Speech and Automatic Speech Recognition
Transformer로 TTS와 STT를 동시에 하는 방법
[Paper Review] Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge
G2P 없이 Lexicon 만으로 TTS 발음 오류를 줄여보자
[Paper Review] Multilingual grapheme-to-phoneme conversion with byte representation
byte로 다중 언어 G2P 성능을 높여보자
[Paper Review] Unified Mandarin TTS Front-end Based on Distilled BERT Model
BERT에서 뽑아낸 feature로 중국어 TTS 전처리 과정 단순하게 만들기
[Paper Review] A bi-directional LSTM approach for polyphone disambiguation in mandarin chinese
중국어 G2P를 위한 bi-directional LSTM
[Paper Review] Sequence-to-sequence neural net models for grapheme-to-phoneme conversion
Seq2Seq 기반 G2P
[Paper Review] Grapheme-to-phoneme conversion using Long Short-Term Memory recurrent neural networks
G2P에 LSTM을 처음 적용한 논문
[Paper Review] Multi-Speaker Emotional Text-to-Speech Synthesizer
다양한 감정으로 다화자 음성 합성을 해보자
[Paper Review] Style Tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis
style embedding을 통해 Tacotron으로 합성한 음성의 스타일을 조절해보자
[Paper Review] Generalization Ability of MOS Prediction Networks
MOS를 예측하는 데 생기는 어려움들을 생각해보자
[Paper Review] LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speech
MBNet에서 단점을 파악하고 개선해보자
[Paper Review] MBNet: MOS Prediction for Synthesized Speech with Mean-Bias Network
평가자 정보를 활용해 더 정확하게 MOS를 예측해보자
[Paper Review] FastPitchFormant: Source-Filter Based Decomposed Modeling for Speech Synthesis
FastPitch에 source-filter 이론을 접목시켰다
[Paper Review] FastPitch: Parallel text-to-speech with pitch prediction
FastSpeech2와 거의 동시에 나온 FastSpeech 후속 버전
[Paper Review] Meta-StyleSpeech: Multi-Speaker Adaptive Text-to-Speech Generation
TTS에 meta learning 적용하기
[Paper Review] HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
GAN 기반 보코더의 한계를 극복
[Paper Review] Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
Parallel Tacotron + duration model
[Paper Review] Parallel Tacotron: Non-autoregressive and controllable TTS
Non Autoregressive Tacotron + VAE
[Paper Review] AdaSpeech 3: Adaptive text to speech for spontaneous style
AdaSpeech를 자연스러운 발화가 가능하도록 만들어보자
[Paper Review] AdaSpeech 2: Adaptive text to speech with untranscribed data
AdaSpeech에서 전사가 안된 데이터를 활용해서 TTS를 할 수 있게 만들어보자
[Paper Review] AdaSpeech: Adaptive text to speech for custom voice
적은 양의 데이터로 개인화 음성을 합성해보자
[Paper Review] Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesis
스펙트로그램 없이 end-to-end TTS 하기
[Paper Review] Glow-TTS: A generative flow for text-to-speech via monotonic alignment search
Flow 기반의 TTS 모델
[Paper Review] Melgan: Generative adversarial networks for conditional waveform synthesis
GAN 기반의 빠르고 효율적인 보코더
[Paper Review] Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram
GAN loss와 새로운 loss를 결합하여 TTS를 하는 모델
[Paper Review] FastSpeech 2: Fast and high-quality end-to-end text to speech
FastSpeech에서 teacher forcing을 제거한 모델
[Paper Review] FastSpeech: Fast, robust and controllable text to speech
Transformer 기반의 빠르고 조절 가능한 TTS 모델
[Paper Review] All about Tacotron 1,2
Tacotron 1,2 리뷰
TTS
[Paper Review] Should you use a probabilistic duration model in TTS? Probably! Especially for spontaneous speech
TTS에서 probabilistic duration model이 효과적인 상황 탐구
[Paper Review] Multi-Speaker Emotional Text-to-Speech Synthesizer
다양한 감정으로 다화자 음성 합성을 해보자
[Paper Review] Style Tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis
style embedding을 통해 Tacotron으로 합성한 음성의 스타일을 조절해보자
[Paper Review] Generalization Ability of MOS Prediction Networks
MOS를 예측하는 데 생기는 어려움들을 생각해보자
[Paper Review] LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speech
MBNet에서 단점을 파악하고 개선해보자
[Paper Review] MBNet: MOS Prediction for Synthesized Speech with Mean-Bias Network
평가자 정보를 활용해 더 정확하게 MOS를 예측해보자
[Paper Review] FastPitchFormant: Source-Filter Based Decomposed Modeling for Speech Synthesis
FastPitch에 source-filter 이론을 접목시켰다
[Paper Review] FastPitch: Parallel text-to-speech with pitch prediction
FastSpeech2와 거의 동시에 나온 FastSpeech 후속 버전
[Paper Review] Meta-StyleSpeech: Multi-Speaker Adaptive Text-to-Speech Generation
TTS에 meta learning 적용하기
[Paper Review] HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
GAN 기반 보코더의 한계를 극복
[Paper Review] Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
Parallel Tacotron + duration model
[Paper Review] Parallel Tacotron: Non-autoregressive and controllable TTS
Non Autoregressive Tacotron + VAE
[Paper Review] AdaSpeech 3: Adaptive text to speech for spontaneous style
AdaSpeech를 자연스러운 발화가 가능하도록 만들어보자
[Paper Review] AdaSpeech 2: Adaptive text to speech with untranscribed data
AdaSpeech에서 전사가 안된 데이터를 활용해서 TTS를 할 수 있게 만들어보자
[Paper Review] AdaSpeech: Adaptive text to speech for custom voice
적은 양의 데이터로 개인화 음성을 합성해보자
[Paper Review] Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesis
스펙트로그램 없이 end-to-end TTS 하기
[Paper Review] Glow-TTS: A generative flow for text-to-speech via monotonic alignment search
Flow 기반의 TTS 모델
[Paper Review] FastSpeech 2: Fast and high-quality end-to-end text to speech
FastSpeech에서 teacher forcing을 제거한 모델
[Paper Review] FastSpeech: Fast, robust and controllable text to speech
Transformer 기반의 빠르고 조절 가능한 TTS 모델
[Paper Review] All about Tacotron 1,2
Tacotron 1,2 리뷰
G2P
[Paper Review] NN-KOG2P: A Novel Grapheme-To-Phoneme Model for Korean Language
한국어의 발음특성을 고려한 FFNN G2P 모델
[Paper Review] Label Embedding for Chinese Grapheme-to-Phoneme Conversion
contrastive learning을 활용한 중국어 G2P
[Paper Review] Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge
G2P 없이 Lexicon 만으로 TTS 발음 오류를 줄여보자
[Paper Review] Multilingual grapheme-to-phoneme conversion with byte representation
byte로 다중 언어 G2P 성능을 높여보자
[Paper Review] Unified Mandarin TTS Front-end Based on Distilled BERT Model
BERT에서 뽑아낸 feature로 중국어 TTS 전처리 과정 단순하게 만들기
[Paper Review] A bi-directional LSTM approach for polyphone disambiguation in mandarin chinese
중국어 G2P를 위한 bi-directional LSTM
Time Series
[Paper Review] Informer: Beyond Efficient Transformer for Long Sequence Time-Series
긴 시계열 예측에 특화된 트랜스포머 모델
[Paper Review] Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models
비정상성을 가진 시계열 데이터를 위한 새로운 Loss function 제안
[Paper Review] Adversarial sparse transformer for time series forecasting
GAN을 활용한 Transformer 훈련
[Paper Review] N-BEATS: Neural Basis Expansion Analysis for Interpretable Time Series Forecasting
오직 딥러닝 아키텍처만을 이용한 TS모델
[Paper Review] Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting
트랜스포머를 활용한 multi-horizon time-series 예측
Transformer
[Paper Review] FastSpeech 2: Fast and high-quality end-to-end text to speech
FastSpeech에서 teacher forcing을 제거한 모델
[Paper Review] FastSpeech: Fast, robust and controllable text to speech
Transformer 기반의 빠르고 조절 가능한 TTS 모델
[Paper Review] Informer: Beyond Efficient Transformer for Long Sequence Time-Series
긴 시계열 예측에 특화된 트랜스포머 모델
[Paper Review] Adversarial sparse transformer for time series forecasting
GAN을 활용한 Transformer 훈련
[Paper Review] Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting
트랜스포머를 활용한 multi-horizon time-series 예측
GAN
[Paper Review] HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
GAN 기반 보코더의 한계를 극복
[Paper Review] Melgan: Generative adversarial networks for conditional waveform synthesis
GAN 기반의 빠르고 효율적인 보코더
[Paper Review] Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram
GAN loss와 새로운 loss를 결합하여 TTS를 하는 모델
[Paper Review] Adversarial audio synthesis
오디오 합성에 처음으로 GAN을 적용한 WaveGAN을 소개하는 논문
[Paper Review] Adversarial sparse transformer for time series forecasting
GAN을 활용한 Transformer 훈련
Neural Codec Language Model
Custom Voice
[Paper Review] AdaSpeech 3: Adaptive text to speech for spontaneous style
AdaSpeech를 자연스러운 발화가 가능하도록 만들어보자
[Paper Review] AdaSpeech 2: Adaptive text to speech with untranscribed data
AdaSpeech에서 전사가 안된 데이터를 활용해서 TTS를 할 수 있게 만들어보자
[Paper Review] AdaSpeech: Adaptive text to speech for custom voice
적은 양의 데이터로 개인화 음성을 합성해보자
MOS
[Paper Review] Generalization Ability of MOS Prediction Networks
MOS를 예측하는 데 생기는 어려움들을 생각해보자
[Paper Review] LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speech
MBNet에서 단점을 파악하고 개선해보자
[Paper Review] MBNet: MOS Prediction for Synthesized Speech with Mean-Bias Network
평가자 정보를 활용해 더 정확하게 MOS를 예측해보자
Zero-Shot
ASR
[Paper Review] End-to-end Music-mixed Speech Recognition
배경음악이 깔린 상황에서 음성인식을 할 수 있는 모델
Survey
Finance
[Paper Review] Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting
트랜스포머를 활용한 multi-horizon time-series 예측
Stock Price Prediction
[Paper Review] Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting
트랜스포머를 활용한 multi-horizon time-series 예측
Vocoder
[Paper Review] Melgan: Generative adversarial networks for conditional waveform synthesis
GAN 기반의 빠르고 효율적인 보코더
[Paper Review] Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram
GAN loss와 새로운 loss를 결합하여 TTS를 하는 모델
Flow
[Paper Review] Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesis
스펙트로그램 없이 end-to-end TTS 하기
VAE
[Paper Review] Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
Parallel Tacotron + duration model
[Paper Review] Parallel Tacotron: Non-autoregressive and controllable TTS
Non Autoregressive Tacotron + VAE
Style Embedding
[Paper Review] Style Tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis
style embedding을 통해 Tacotron으로 합성한 음성의 스타일을 조절해보자
[Paper Review] Meta-StyleSpeech: Multi-Speaker Adaptive Text-to-Speech Generation
TTS에 meta learning 적용하기
LSTM
[Paper Review] A bi-directional LSTM approach for polyphone disambiguation in mandarin chinese
중국어 G2P를 위한 bi-directional LSTM
Speaker Generation
[Paper Review] Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech
사람의 얼굴에 어울리는 목소리를 자동으로 만들어주는 디퓨전 기반 TTS 모델
[Paper Review] VoiceMe: Personalized voice generation in TTS
인물의 사진을 보고 어울리는 음성을 직접 제작할 수 있는 모델
Audio Compression
[Paper Review] High Fidelity Neural Audio Compression
SoundStream 보다 발전된 뉴럴 오디오 코덱
[Paper Review] SoundStream: An End-to-End Neural Audio Codec
최초의 End-to-End 뉴럴 오디오 코덱
Codec
[Paper Review] High Fidelity Neural Audio Compression
SoundStream 보다 발전된 뉴럴 오디오 코덱
[Paper Review] SoundStream: An End-to-End Neural Audio Codec
최초의 End-to-End 뉴럴 오디오 코덱
Anti Spoofing
Audio Deepfake Detection
Speech Processing
Back to top ↑SR
Back to top ↑SER
Back to top ↑Financial Engineering
[Book Review] 처음 만나는 금융공학
금융공학 입문용 책
Loss Function
[Paper Review] Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models
비정상성을 가진 시계열 데이터를 위한 새로운 Loss function 제안
Dynamic Time Warping
[Paper Review] Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models
비정상성을 가진 시계열 데이터를 위한 새로운 Loss function 제안
Long Sequence
[Paper Review] Informer: Beyond Efficient Transformer for Long Sequence Time-Series
긴 시계열 예측에 특화된 트랜스포머 모델
Audio Synthesis
[Paper Review] Adversarial audio synthesis
오디오 합성에 처음으로 GAN을 적용한 WaveGAN을 소개하는 논문
Neural Vocoder
Meta Learning
[Paper Review] Meta-StyleSpeech: Multi-Speaker Adaptive Text-to-Speech Generation
TTS에 meta learning 적용하기
Multi Speaker
[Paper Review] Multi-Speaker Emotional Text-to-Speech Synthesizer
다양한 감정으로 다화자 음성 합성을 해보자
Seq2Seq
BERT
[Paper Review] Unified Mandarin TTS Front-end Based on Distilled BERT Model
BERT에서 뽑아낸 feature로 중국어 TTS 전처리 과정 단순하게 만들기
Byte representation
[Paper Review] Multilingual grapheme-to-phoneme conversion with byte representation
byte로 다중 언어 G2P 성능을 높여보자
Lexicon
[Paper Review] Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge
G2P 없이 Lexicon 만으로 TTS 발음 오류를 줄여보자
Speech Recognition
[Paper Review] Almost Unsupervised Text to Speech and Automatic Speech Recognition
Transformer로 TTS와 STT를 동시에 하는 방법
Contrastive Learning
[Paper Review] Label Embedding for Chinese Grapheme-to-Phoneme Conversion
contrastive learning을 활용한 중국어 G2P
Diffusion
[Paper Review] Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
Diffusion Probabilistic Model 기반 decoder를 사용한 TTS 모델
Prompt TTS
Natural Language Guidance
Duration
[Paper Review] Should you use a probabilistic duration model in TTS? Probably! Especially for spontaneous speech
TTS에서 probabilistic duration model이 효과적인 상황 탐구
Flow Matching
[Paper Review] Should you use a probabilistic duration model in TTS? Probably! Especially for spontaneous speech
TTS에서 probabilistic duration model이 효과적인 상황 탐구
Spontaneous Speech
[Paper Review] Should you use a probabilistic duration model in TTS? Probably! Especially for spontaneous speech
TTS에서 probabilistic duration model이 효과적인 상황 탐구
Cross-Lingual TTS
Back to top ↑Speech-to-Speech
Back to top ↑Code Switching
Back to top ↑GNN
Back to top ↑AI Agent
[Class Review] Unit 1: Introduction to Agents (Part 1)
Hugging Face Agents Course
Hugging Face
[Class Review] Unit 1: Introduction to Agents (Part 1)
Hugging Face Agents Course
LLM
[Class Review] Unit 1: Introduction to Agents (Part 1)
Hugging Face Agents Course
Online Course
[Class Review] Unit 1: Introduction to Agents (Part 1)
Hugging Face Agents Course