A method and an apparatus for speech signal processing are provided. The method includes: receiving an encoded speech signal sent by a user equipment, where the encoded speech signal includes a first substream, a second substream, and a third substream, and the first substream is attached with a cyclic redundancy check (CRC); performing decoding processing on the first substream, the second substream, and the third substream by adopting a decoding algorithm, where a decoding algorithm that is based on an auxiliary decision of the CRC is adopted to perform decoding processing on the first substream; and sending decoding results of the first substream, the second substream, and the third substream to a base station controller, where the decoding result of the first substream includes a decoded bit stream and a CRC result. Decoding performance of the first substream is improved, and users' higher requirements for the speech quality are met.