Example methods include receiving training data comprising a plurality of audio clips and a plurality of textual descriptions of audio. The methods include generating a shared representation comprising a joint embedding. An audio embedding of a given audio clip is within a threshold distance of a text embedding of a textual description of the given audio clip. The methods include generating, based on the joint embedding, a conditioning vector and training, based on the conditioning vector, a neural network to: receive (i) an input audio waveform, and (ii) an input comprising one or more of an input textual description of a target audio source in the input audio waveform, or an audio sample of the target audio source, separate audio corresponding to the target audio source from the input audio waveform, and output the separated audio corresponding to the target audio source in response to the receiving of the input.