Investigating phonetic information reduction and lexical confusability
نویسندگان
چکیده
In the presence of pronunciation variation and the masking effects of additive noise, we investigate the role of phonetic information reduction and lexical confusability on ASR performance. Contrary to previous work [1], we show that place of articulation as a representation for unstressed segments performs at least as well as manner of articulation in the presence of additive noise. Methods of phonetic reduction introduce lexical confusibility which negatively impact performance. By limiting this confusability, recognizers that employ high levels of phonetic reduction (40.1%) can perform as well a baseline system in the presence of nonstationary noise.
منابع مشابه
Effects of context-sensitive phonetic variation and lexical structure on the uniqueness of words
Phonetic context can affect speechreading confusions for phonemes. h Experiment I, behavioral experiments were performed to examine effects of context-sensitive phonetic variation on the visual confusability of consonants and vowels. h Experiment H, compubtional experiments were perfomed to assess the importance of patterns of context-sensitive visual codusability on the uniqueness of words in ...
متن کاملProduction of English Lexical Stress by Persian EFL Learners
This study examines the phonetic properties of lexical stress in English produced by Persian speakers learning English as a foreign language. The four most reliable phonetic correlates of English lexical stress, namely fundamental frequency, duration, intensity, and vowel quality were measured across Persian speakers’ production of the stressed and unstressed syllables of five English disyllabi...
متن کاملSentence recognition materials based on frequency of word use and lexical confusability.
The sentence stimuli developed in this project combined aspects from several traditional approaches to speech audiometry. Sentences varied with respect to frequency of word use and phonetic confusability. Familiar consonant-vowel-consonant words, nouns and modifiers, were used to form 500 sentences of seven to nine syllables. Based on concepts from the Neighborhood Activation Model for spoken w...
متن کاملExplaining the visual and masked-visual advantage in speech perception in noise: the role of visual phonetic cues
Visual enhancement of speech intelligibility, although clearly established, still resists a clear description. We attempt to contribute to solving that problem by proposing a simple account based on phonetically motivated visual cues. This work extends a previous study quantifying the visual advantage in sentence intelligibility across three conditions with varying degrees of visual information...
متن کاملPronunciation lexicon modeling and design for Korean large vocabulary continuous speech recognition
In this paper, we describe a pronunciation lexicon model which is especially useful for constructing morpheme-based pronunciation lexicon to improve the performance of a Korean LVCSR. There are a lot of pronunciation variations occurring at morpheme boundaries in continuous speech. For modeling of cross-morpheme pronunciation variations, we usually used a context-dependent multiple pronunciatio...
متن کامل