| 摘要 |
<p>A speech recognition feature extractor (200, FE) for extracting speech features from a speech signal, comprising: a time-to-frequency domain transformer (210) for generating spectral values in the frequency domain from the speech signal; a partitioning means (235) for generating a first set of spectral values in the frequency domain and an additional set of spectral values in the frequency domain; a first feature generator (240) for generating a first group of speech features using the first set of spectral values; a additional feature generator (250) for generating an additional group of speech features using the additional set of spectral values; and an assembler (260) for assembling an output set of speech features from at least one speech feature from the first group of speech features and at least one speech feature from the additional group of speech features, where the first and the additional set of spectral values comprise at least one common spectral value. A respective back-end, speech recognition system, telecommunications network, speech feature extracting method, spoken information recognising methods, and computer program products are also described.</p> |
