Detection of Pre-Recorded Messages in Speech

Recognition of pre-recorded messages in speech is useful for any follow-up speech data mining. This thesis summarises the theory of searching similar utterances in speech and efficient approaches to compare two sequences. To investigate identification of redundant information in audio, it is necessary to have a large amount of data with the exact phrases repeated multiple times. We generated a dataset by mixing pre-recorded messages into phone calls with variations in speed, volume and repetitions. Our system tackles known messages and unknown messages'' scenarios by using approaches like clustering or detection in chunks. Dynamic time warping, approximate string matching and recurrent quantification analysis are compared, and finally, all mentioned techniques are combined to obtain a precise and efficient system.

detection of re-occurring sequences in audio, segmental dynamic time warping, recurrence quantification analysis, fuzzy string matching, bottleneck features, phoneme posteriors, Mel-frequency cepstral coefficients features