ABSTRACT:

In this paper we tend to gift 2 voice-to-phoneme conversion algorithms that extract voice-tag abstactions for speaker-independent voice-tag applications in embedded platforms, that are very sensitive to memory and CPU consumptions. In the first approach, a voice-to-phoneme conversion in batch mode manages this task by preserving the commonality of input feature vectors of multiple voice-tag example utterances. Given multiple example utterances, a developed feature combination strategy produces an "average" utterance, that is converted to phonetic strings as a voice-tag representation via a speaker-freelance phonetic decoder. In the second approach, a sequential voice-to-phoneme conversion algorithm uncovers the hierarchy of phonetic consensus embedded among multiple phonetic hypotheses generated by a speaker-independent phonetic decoder from multiple example utterances of a voice-tag. The most relevant phonetic hypotheses are then chosen to represent the voice-tag. The voice-tag representations obtained by these 2 voice-to-phoneme conversion algorithms are compared in Speech Recognition experiments to phonetic transcriptions of voice-tag reference prepared by an skilled phonetician. Both algorithms either perform comparably to or considerably better than the manual transcription approach. We have a tendency to conclude from this that both algorithms are terribly effective for the targeted purposes