Automatic scoring of pronunciation quality

Neumeyer, Leonardo; Franco, Horacio; Digalakis, Vassilios; Weintraub, M.

doi:10.1016/s0167-6393(99)00046-1

Cited by 183 publications

(99 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is believed that teachers are the source of knowledge, so students are used to the passive learning mode with teachers as the center [12]. As a consequence, most of them rest strongly on teachers.…”

Section: B Factors Affecting Active Learningmentioning

confidence: 99%

Research and Software Development of Active Learning Mode for College Students Based on Computer Network

2016

Int. J. Emerg. Technol. Learn.

View full text Add to dashboard Cite

Abstract-With the development of information technology, especially the fast development of Internet technology, the network technology has expanded to all walks of life. Using Internet to acquire knowledge has become an important means for us. The paper sums up the current status of foreign active learning modes and the problems existing in computer network environment by referring to the relevant literature. What is more, it also further clarifies the basic concepts and connotations of active learning in the computer network environment and active learning itself by researching on its relevant theoretical basis and influential factors as well. "A new active learning mode in computer network environment" is constructed based on the analysis of the relevant factors of active learning in the computer network environment, taking college students as the studying object and the college English course as an example. According to this model, the active learning platform of college English network is designed and developed. The research conclusion is not only theoretically based, but also founded on the concrete practice and the application. Therefore, it is endowed with maneuverability so as to provide a research example for the general teachers.Index Terms-Internet technology; active learning mode; computer network environment; platform of college English

show abstract

Section: B Factors Affecting Active Learningmentioning

confidence: 99%

Research and Software Development of Active Learning Mode for College Students Based on Computer Network

2016

Int. J. Emerg. Technol. Learn.

View full text Add to dashboard Cite

show abstract

“…Witt (Witt, 1999) developed the Goodness of Pronunciation (GOP) measurement for measuring pronunciation based on Hidden Markov Model (HMM) log likelihood. Using a similar method, Neumeyer et al (Neumeyer et al, 2000) designed a series of likelihood related pronunciation features, e.g., the local average likelihood and global average likelihood. Hacker et al (Hacker et al, 2005) utilized a relatively large feature vector for scoring pronunciation.…”

Section: Related Workmentioning

confidence: 99%

Improved pronunciation features for construct-driven assessment of non-native spontaneous speech

Chen

Zechner

2009

Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Com

View full text Add to dashboard Cite

This paper describes research on automatic assessment of the pronunciation quality of spontaneous non-native adult speech. Since the speaking content is not known prior to the assessment, a two-stage method is developed to first recognize the speaking content based on non-native speech acoustic properties and then forced-align the recognition results with a reference acoustic model reflecting native and near-native speech properties. Features related to Hidden Markov Model likelihoods and vowel durations are extracted. Words with low recognition confidence can be excluded in the extraction of likelihood-related features to minimize erroneous alignments due to speech recognition errors. Our experiments on the TOEFL R Practice Online test, an English language assessment, suggest that the recognition/forced-alignment method can provide useful pronunciation features. Our new pronunciation features are more meaningful than an utterance-based normalized acoustic model score used in previous research from a construct point of view.

show abstract

“…Accent rating-the degree of foreign accent or type of accent of a talker-is a perceptual evaluation task that is relevant to a variety of different tasks within speech technology, e.g., in computer assisted language learning [1,2], for accent conversion [3,4], for accent identification [5,6], to reduce the impact of non-native accents on word error rates in ASR [7,8], and in the context of adverse listening conditions [9]. The study presented here was conducted in the context of an EU project which aimed for personalized speech-to-speech translation such that a user's spoken input in one language was used to produce spoken output in another language, while continuing to sound like the user's voice [10].…”

Section: Introductionmentioning

confidence: 99%

Accent rating by native and non-native listeners

Wester

Mayo

2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This study investigates the influence of listener native language with respect to talker native language on perception of degree of foreign accent in English. Listeners from native English, Finnish, German and Mandarin backgrounds rated the accentedness of native English, Finnish, German and Mandarin talkers producing a controlled set of English sentences. Results indicate that non-native listeners, like native listeners, are able to classify non-native talkers as foreign-accented, and native talkers as unaccented. However, while non-native talkers received higher accentedness ratings than native talkers from all listener groups, non-native listeners judged talkers with non-native accents less harshly than did native English listeners. Similarly, non-native listeners assigned higher degrees of foreign accent to native English talkers than did native English listeners. It seems that non-native listeners give accentedness ratings that are less extreme, or closer to the centre of the rating scale in both directions, than those used by native listeners.

show abstract

Automatic scoring of pronunciation quality

Cited by 183 publications

References 7 publications

Research and Software Development of Active Learning Mode for College Students Based on Computer Network

Research and Software Development of Active Learning Mode for College Students Based on Computer Network

Improved pronunciation features for construct-driven assessment of non-native spontaneous speech

Accent rating by native and non-native listeners

Contact Info

Product

Resources

About