数据集:

3Aaishell 3Acommonvoice 3Acommon_voice 3ADEMAND 3ADvoice 3Agoogle+speech+commands 3Aiemocap 3ALibri2Mix 3ALibri3Mix 3ALibrispeech 3ALibriTTS 3ALJSpeech 3ATimers+and+Such 3AUrbansound8k 3AVoicebank 3Avoxceleb 3AVoxLingua107 3Avoxpopuli 3AWHAM! 3AWHAMR! 3AWSJ0-2Mix 3AWSJ0-3Mix aishell commonvoice common_voice DEMAND Dvoice google speech commands iemocap Libri2Mix Libri3Mix LibriTTS LJSpeech Timers and Such Urbansound8k Voicebank voxceleb VoxLingua107 voxpopuli WHAMR! WSJ0-2Mix WSJ0-3Mix

语言:

ar dar en fr multilingual

预印本库:

arxiv:1712.05884 arxiv:1804.03209 arxiv:2010.05646 arxiv:2010.13154 arxiv:2104.01604 arxiv:2106.04624 arxiv:2111.00161 arxiv:2207.13703

其他:

Attention Audio Source Separation Audio+Source+Separation audio-source-separation Command Recognition Command+Recognition Commands CommonLanguage CRDNN CTC ECAPA ECAPA-TDNN embeddings Emotion G2P Grapheme-to-Phoneme hf-asr-leaderboard HiFIGAN Identification Keyword Spotting Keyword+Spotting Keywords Language LibriSpeech LibryParty mctct Eval Results PyTorch Recognition Robust ASR Robust+ASR SAD SepFormer Sound Source Separation Source+Separation Speaker Speaker Diarization Speaker+Diarization speech Speech Activity Detection Speech Enhancement Speech Separation Speech+Activity+Detection Speech+Enhancement Speech+Separation speech-enhancement speech-synthesis Spoken language understanding Spoken+language+understanding Tacotron2 TDNN Transformer Transformers TTS VAD Verification Vocoder Voice Activity Detection Voice+Activity+Detection wav2vec2 WHAM! WSJ02Mix xvectors

任务:

音频分类 音频到音频 自动语音识别 文本转语音 文生文

许可:

apache-2.0 cc0-1.0

类库:

speechbrain