Speech synthesis method, speech synthesis model training method, speech synthesis model training device and speech synthesis model training equipment

The invention discloses a speech synthesis method, a speech synthesis model training method, a speech synthesis model training device and speech synthesis model training equipment. In one embodiment of the invention, the speech synthesis method comprises the following steps of carrying out text coding on a to-be-synthesized first text to obtain a first synthesis feature; performing acoustic coding on the first acoustic feature to obtain a second synthetic feature; performing alignment processing on the first synthetic feature, the second synthetic feature and pre-selected speaker identification information to obtain a third synthetic feature; and carrying out acoustic decoding on the third synthetic feature to obtain a second acoustic feature of the first text. According to the method, speech synthesis of multiple speakers can be realized through one speech synthesis model. 公开了一种语音合成方法及语音合成模型的训练方法、装置、设备。本公开的一实施例中，语音合成方法可以包括：对待合成的第一文本进行文本编码，获得第一合成特征；对第一声学特征进行声学编码，获得第二合成特征；对所述第一合成特征、第二合成特征和预先选定的发音人标识信息进行对齐处理，获得