PK PyTorchKR Papers
Papers with Code · CC BY-SA 4.0

Speech Synthesis

Accented Speech Recognition › Speech Synthesis 44 평가 기록 18 datasets

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>

개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.

벤치마크

Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.

Dataset기록된 모델 예시MetricPaperCode
PeriodWave-Turbo-L
PESQ: 4.454Periodicity: 0.0528V/UV F1: 0.9756M-STFT: 0.7358
논문 코드
Tacotron 2
Mean Opinion Score: 4.526
논문 코드
BDDM vocoder
Mean Opinion Score: 4.48
논문 코드
WaveNet (L+F)
Mean Opinion Score: 4.08
논문 코드
SampleRNN (3-tier)
NLL: 1.387
논문 코드
AI4BharatTTS - FastPitch with HiFiGAN
Mean Opinion Score: 3.58
논문 코드
AI4BharatTTS - FastPitch with HiFiGAN
Mean Opinion Score: 3.84
논문 코드
AI4BharatTTS - FastPitch with HiFiGAN
Mean Opinion Score: 3.68
논문 코드
AI4BharatTTS - FastPitch with HiFiGAN
Mean Opinion Score: 3.64
논문 코드
AI4BharatTTS - FastPitch with HiFiGAN
Mean Opinion Score: 3.66
논문 코드
AI4BharatTTS - FastPitch with HiFiGAN
Mean Opinion Score: 2.39
논문 코드
AI4BharatTTS - FastPitch with HiFiGAN
Mean Opinion Score: 3.37
논문 코드

데이터셋

18개
LibriTTSNorth American EnglishLJSpeechMandarin ChineseBlizzard Challenge 2013IndicTTSIndicTTSIndicTTSIndicTTSIndicTTSIndicTTSIndicTTS

논문

라이브러리

Papers with Code 리더보드 row에 연결된 구현 저장소입니다.

github.com/coqui-ai/TTS 2 논문
github.com/2023-MindSpore-1/ms-code-15/tree/main/wavenet 1 논문
github.com/adityaagrawal7/speech-to-text-wavenet 1 논문
github.com/AI-Huang/WaveNet 1 논문
github.com/albarji/neurowriter 1 논문
github.com/anandharaju/Basic_TCN 1 논문
github.com/ashishpatel26/tcn-keras-Examples 1 논문
github.com/awslabs/gluon-ts 1 논문

하위 태스크

SS Speech Synthesis - Gujarati 2 데이터셋 · 2 rows SS Speech Synthesis - Assamese 1 데이터셋 · 1 rows SS Speech Synthesis - Bengali 1 데이터셋 · 1 rows SS Speech Synthesis - Bodo 1 데이터셋 · 1 rows SS Speech Synthesis - Hindi 1 데이터셋 · 1 rows SS Speech Synthesis - Kannada 1 데이터셋 · 1 rows SS Speech Synthesis - Malayalam 1 데이터셋 · 1 rows SS Speech Synthesis - Manipuri 1 데이터셋 · 1 rows SS Speech Synthesis - Marathi 1 데이터셋 · 1 rows SS Speech Synthesis - Rajasthani 1 데이터셋 · 1 rows SS Speech Synthesis - Tamil 1 데이터셋 · 1 rows SS Speech Synthesis - Telugu 1 데이터셋 · 1 rows