A speech-to-speech translation method and apparatus for a language disorder, and a storage medium. The method may comprise: dividing, in accordance with a pre-set separation policy, received non-normal speech information into at least one piece of non-normal sub-speech information (S101); inquiring, according to the non-normal sub-speech information, a pre-set speech database to obtain normal sub-speech information corresponding to the non-normal sub-speech information (S102); and splicing the normal sub-speech information to obtain normal speech information corresponding to the non-normal speech information (S103).
展开▼