Fishing for meaningful units in connected speech

Peter Juel Henrichsen, Thomas Ulrich Christiansen

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review


    In many branches of spoken language analysis including ASR, the set of smallest meaningful units of speech is taken to coincide with the set of phones or phonemes. However, fishing for phones is difficult, error-prone, and computationally expensive. We present an experiment, based on machine learning, with an alternative approach. Instead of stipulating a basic set of target units, the determination of the set is considered to be part of the learning task. Given 18 recordings of Danish talkers performing a simple lab task, our algorithm produced a set of acoustically well-defined units sufficient for identifying all the major semantic elements (be they parts of words, words or several words), relevant to the task. As the sound encoding used was very simple – fundamental frequency (F0), Harmonicity-to-Noise-Ratio (HNR), and Intensity samples only – the computational complexity involved was far lower than for phonemic recognition. Our findings show that it is possible to automatically characterize a linguistic message, without detailed spectral information or presumptions about the target units. Further, fishing for simple meaningful cues and enhancing these selectively would potentially be a more effective way of achieving intelligibility transfer, which is the end goal for speech transducing technologies.
    Original languageEnglish
    Title of host publicationProceedings of ISAAR 2009
    EditorsJörg Buchholz, Torsten Dau, Jakob Christensen-Dalsgaard, Torben Poulsen
    Publication date2009
    ISBN (Print)87-990013-2-2
    Publication statusPublished - 2009
    Event2nd International Symposium on Auditory and Audiological Research: Binaural Processing and Spatial Hearing - Marienlyst, Helsingør, Denmark
    Duration: 26 Aug 200928 Aug 2009


    Conference2nd International Symposium on Auditory and Audiological Research
    Internet address


    Dive into the research topics of 'Fishing for meaningful units in connected speech'. Together they form a unique fingerprint.

    Cite this