首页>
外国专利>
TARGETED VOICE SEPARATION BY SPEAKER CONDITIONED ON SPECTROGRAM MASKING
TARGETED VOICE SEPARATION BY SPEAKER CONDITIONED ON SPECTROGRAM MASKING
展开▼
机译:在频谱图制作条件下通过扬声器进行有针对性的语音分离
展开▼
页面导航
摘要
著录项
相似文献
摘要
Techniques are disclosed that enable processing of audio data to generate one or more refined versions of audio data, where each of the refined versions of audio data isolate one or more utterances of a single respective human speaker. Various implementations generate a refined version of audio data that isolates utterance(s) of a single human speaker by processing a spectrogram representation of the audio data (generated by processing the audio data with a frequency transformation) using a mask generated by processing the spectrogram of the audio data and a speaker embedding for the single human speaker using a trained voice filter model. Output generated over the trained voice filter model is processed using an inverse of the frequency transformation to generate the refined audio data.
展开▼