Papers with Code 아카이브
Speech Synthesis
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Jejueo Datasets for Machine Translation and Speech Synthesis
Cross-lingual Multi-speaker Text-to-speech Synthesis for Voice Cloning without Using Parallel Corpus for Unseen Speakers
Independent and automatic evaluation of acoustic-to-articulatory inversion models
A unified sequence-to-sequence front-end model for Mandarin text-to-speech synthesis
Incremental Text-to-Speech Synthesis with Prefix-to-Prefix Framework
ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech
What does a network layer hear? Analyzing hidden representations of end-to-end ASR through speech synthesis
Spoofing Speaker Verification Systems with Deep Multi-speaker Text-to-speech Synthesis
Replay Spoofing Countermeasure Using Autoencoder and Siamese Network on ASVspoof 2019 Challenge
Effect of choice of probability distribution, randomness, and search methods for alignment modeling in sequence-to-sequence text-to-speech synthesis using hard alignment
Transferring neural speech waveform synthesizers to musical instrument sounds generation
Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram
Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis
Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models
The Theory behind Controllable Expressive Speech Synthesis: a Cross-disciplinary Approach
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
Semi-Supervised Generative Modeling for Controllable Speech Synthesis
Attention Forcing for Sequence-to-sequence Model Training
High Fidelity Speech Synthesis with Adversarial Networks
Speech Recognition with Augmented Synthesized Speech
Disentangling Speech and Non-Speech Components for Building Robust Acoustic Models from Found Data
Modular Meta-Learning with Shrinkage
Evaluating Long-form Text-to-Speech: Comparing the Ratings of Sentences and Paragraphs
DurIAN: Duration Informed Attention Network For Multimodal Synthesis
Maximizing Mutual Information for Tacotron
Neural Harmonic-plus-Noise Waveform Model with Trainable Maximum Voice Frequency for Text-to-Speech Synthesis
Unpaired Image-to-Speech Synthesis with Multimodal Information Bottleneck
DNN-based Speaker Embedding Using Subjective Inter-speaker Similarity for Multi-speaker Modeling in Speech Synthesis
Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning
Multi-Speaker End-to-End Speech Synthesis
Deep Residual Neural Networks for Audio Spoofing Detection
End-to-End Emotional Speech Synthesis Using Style Tokens and Semi-Supervised Training
RUSLAN: Russian Spoken Language Corpus for Speech Synthesis
A Unified Speaker Adaptation Method for Speech Synthesis using Transcribed and Untranscribed Speech with Backpropagation
Towards Transfer Learning for End-to-End Speech Synthesis from Deep Pre-Trained Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.