Baby cry signal recognition is branch of application of speech recognition. It studied translation of cry signal into text. Using tool to pick up a short time period from a signal, the tools can still assume the signal under processing to be stationary. It may constitute time invariant system and time invariant excitation when it is viewed in blocks of 10-30 msec. A processing is termed as Short Term Processing (STP). Then, using mel-frequency cepstral coefficients (MFCC) and bark frequency cepstral coefficients (BFCC) extract the feature of different known baby cry signal to make the codebook. Set up hidden markov model (HMM) to train estimate baby cry signal. Classify estimate baby cry achieve baby cry signal recognition.

Full text: IJEIR_2070_Final.pdf