Embodiments of methods and apparatuses for recognizing a speech are provided. An implementation can include: determining an identity of a target user inputting the speech input signal; extracting a common expression set of the target user from a stored common expression database, the common expression set including a plurality of common expressions; extracting an acoustic feature of the speech input signal and input the same into an acoustic model to obtain an acoustic model score; judging whether a content of the speech input signal is a common expression of the target user based on the acoustic model score of the speech input signal and acoustic model scores of the common expressions in the stored common expression set of the target user; and if yes, decoding the acoustic feature of the speech input signal using a language model constructed based on common expressions, to obtain a speech recognition result.