Lexical Stress Detection Research Articles

Automatic lexical stress and pitch accent detection for L2 English speech using multi-distribution deep neural networks

This paper investigates the use of multi-distribution deep neural networks (MD-DNNs) for automatic lexical stress detection and pitch accent detection, which are useful for suprasegmental mispronunciation detection and diagnosis in second-language (L2) English speech. The features used in this paper cover syllable-based prosodic features (including maximum syllable loudness, syllable nucleus duration and a pair of dynamic pitch values) as well as lexical and syntactic features (encoded as binary variables). As stressed/accented syllables are more prominent than their neighbors, the two preceding and two following syllables are also taken into consideration. Experimental results show that the MD-DNN for lexical stress detection achieves an accuracy of 87.9% in syllable classification (primary/secondary/no stress) for words with three or more syllables. This performance is much better than those of our previous work using Gaussian mixture models (GMMs) and the prominence model (PM), whose accuracies are 72.1% and 76.3% respectively. Approached similarly as the lexical stress detector, the pitch accent detector obtains an accuracy of 90.2%, which is better than the results of using the GMMs and PM by about 9.6% and 6.9% respectively.

Demonstration of Problems of Lexical Stress on the Pronunciation Turkish English Teachers and Teacher Trainees by Computer

Abstract Stress is an important intonational and prosodic feature both in North American English (NAE) and Brtish English (BrE.); therefore, lexical stress placement of the speaker and its perception as lexical stress detection occupy a crucial role in teaching English as a foreign language. The identification, determination and assignment of lexical stress are crucial issues because the perception of stressed syllables can provide non-native speaking teachers islands of reliability where the phonetic information is more prominent. But still the issue of stress assignment has not received much attention in foreign language teacher training programs. This paper stresses that nuclear stress placement has important implications for non-native speaking teachers.

Application of pitch synchronization dynamic frame-length features in English lexical stress detection

Lexical stress is an important prosodic feature,especially for stress-timed language such as English.To overcome the defects of fixed frame-length features,pitch synchronization feature analysis method was proposed while Pitch Synchronization Energy(PSE) and Pitch Synchronization Peak(PSP) features were defined and extracted.Their contributions,along with traditional features and their combinations,to English lexical stress detection were evaluated with ISLE database.Experimental results show that the combination of new feature and traditional features demonstrates a 6.65% error rate reduction compared with using traditional ones.

Lexical stress detection in isolated English words

Two experiments are reported concerning the detection of lexical stress in isolated English words. A non-statistical method using rules based on pitch variations is proposed. Better results are obtained with this method than when using static values of pitch as stress correlates. To avoid the problem of syllable segmentation, two methods based on pitch and energy function contours are presented to find stressed regions in words. These regions can be considered as regions of phonetic reliability. The second experiment analyzes lexical stress in words pronounced with a rising pitch. Maximum energy is reported to be the best correlate of stress, followed by duration. Finally, it is proposed that the study of lexical stress in continuous speech be accompanied by the study of prosodics and their general use in sentences.