Sonority Contours in Speech Recognition
نویسندگان
چکیده
for their invaluable input into this paper. All errors are my own. The sonority scale that ranks phonemes according to relative " loudness " has long played a significant role in the fields of Phonology and Historical Linguistics, yet it is conspicuously absent from the speech recognition literature. In this preliminary study using the Hoosier Mental Lexicon, it was found that approximately half of the 20,000 words in the lexicon have unique sonority contours. Moreover, it was found that there is no correlation between " sorority " (group of words that share a single sonority contour) size and either word frequency or familiarity. Each sorority is indistinguishable from a random sample of words with respect to these two criteria. This implies that sonority contours may constitute an independent factor in word recognition that may have effects analogous to frequency. Sororities may also have implications for defining word neighborhoods.
منابع مشابه
Sonority Measure for Automatic Speech Recognition
In this paper, the use of sonority measure as an acoustic feature of the speech signal for continuous automatic speech recognition is described. The representation of sonority extent of sounds is made with a help of spectrum derivation. Therefore, a novel articulatory motivated acoustic feature expressing the sonority is named spectrum derivative feature. The new feature is tested in combinatio...
متن کاملMandarin-Speaking Children’s Speech Recognition: Developmental Changes in the Influences of Semantic Context and F0 Contours
The goal of this developmental speech perception study was to assess whether and how age group modulated the influences of high-level semantic context and low-level fundamental frequency (F0) contours on the recognition of Mandarin speech by elementary and middle-school-aged children in quiet and interference backgrounds. The results revealed different patterns for semantic and F0 information. ...
متن کاملEffects of Semantic Context and Fundamental Frequency Contours on Mandarin Speech Recognition by Second Language Learners
Speech recognition by second language (L2) learners in optimal and suboptimal conditions has been examined extensively with English as the target language in most previous studies. This study extended existing experimental protocols (Wang et al., 2013) to investigate Mandarin speech recognition by Japanese learners of Mandarin at two different levels (elementary vs. intermediate) of proficiency...
متن کاملSpike-v: an Adaptive Mechanism for Speech-rate Independent Timing
A neuronal model intended to target highly sonorant periods of a speech stream is presented. The model—“Spike-V”—uses habituation and Hebbian learning in opposition to each other to dynamically adjust its behavior. Acting in realtime, driven by only the signal, Spike-V produces a spike-train in which each spike corresponds to roughly the center of a period of high sonority (i.e. a vowel) in the...
متن کاملTone realisation in a yorùbá speech recognition corpus
We investigate the acoustic realisation of tone in short continuous utterances in Yorùbá. Fundamental frequency (F0) contours are extracted for automatically aligned syllables from a speech corpus of 33 speakers collected for speech recognition development. Extracted contours are processed and analysed statistically to describe acoustic properties in different tonal contexts. We demonstrate how...
متن کامل