Patent
Systems and methods for an automated pronunciation assessment system for similar vowel pairs
Reads0
Chats0
TLDR
In this paper, a non-native speech sample is processed to identify a plurality of vowel sound boundaries in the non native speech sample, and the vowel characteristics associated with a first vowel sound and a second vowel sound represented in the sample are extracted.Abstract:
Computer-implemented systems and methods are provided for assessing non-native speech proficiency. a non-native speech sample is processed to identify a plurality of vowel sound boundaries in the non-native speech sample. Portions of the non-native speech sample are analyzed within the vowel sound boundaries to extract vowel characteristics associated with a first vowel sound and a second vowel sound represented in the non-native speech sample. The vowel characteristics are processed to identify a first vowel pronunciation metric for the first vowel sound and a second vowel pronunciation metric for the second vowel sound, and the first vowel pronunciation metric and the second vowel pronunciation metric are processed to determine whether the non-native speech sample exhibits a distinction in pronunciation of the first vowel sound and the second vowel sound.read more
Citations
More filters
Patent
Systems and Methods for Automated Evaluation of Human Speech
Okim Kang,David O. Johnson +1 more
TL;DR: In this paper, a microphone coupled with a computing device comprising a microprocessor, a memory, and a display operatively coupled together is used to evaluate human speech proficiency in a language.
Patent
Systems and methods for human speech training
TL;DR: In this article, sound samples produced by a speaker are transcribed and analyzed against database sound samples to provide speech therapy, compute the accuracy of a speaker's pronunciation, aid in learning a foreign language, and help members of the deaf community learn to communicate with spoken language.
Patent
Processor-implemented systems and methods for determining sound quality
Zhou Yu,Vikram Ramanarayanan,David Suendermann-Oeft,Xinhao Wang,Klaus Zechner,Lei Chen,Jidong Tao,Yao Qian +7 more
TL;DR: In this article, a processor-implemented method of analyzing quality of sound acquired via a microphone is presented, where an input metric is extracted from a sound recording at each of a plurality of time intervals, and the output metric is aggregated from each of the time intervals to generate a score indicative of the quality of the sound obtained via the microphone.
Patent
Spoken language examination system and method
Ma Hengwei,Yang Bo +1 more
TL;DR: In this article, a spoken language examination system and method consisting of a central server and an examination terminal is presented. But the system is not suitable for the use of mobile devices and does not have the benefits of low cost, high efficiency and guarantee of examination fairness.
Patent
Native language identification with time delay deep neural networks trained separately on native and non-native english corpora
TL;DR: In this article, a native language identification system, comprising a plurality of artificial neural networks such as time delay deep neural networks, is provided, which is trained as universal background models, using separate native language and non-native language corpora.
References
More filters
Journal ArticleDOI
Age Constraints on Second-Language Acquisition
James Emil Flege,James Emil Flege,Grace H. Yeni-Komshian,Grace H. Yeni-Komshian,Serena Liu,Serena Liu +5 more
TL;DR: The authors evaluated the critical period hypothesis for second language (L2) acquisition and found that the observed decrease in morphosyntax scores was not the result of passing a maturationally defined critical period.
Journal ArticleDOI
Effects of experience on non-native speakers' production and perception of English vowels
TL;DR: The authors assessed the effect of English language experience on non-native speakers' production and perception of English vowels and found that the experienced nonnative subjects produced and perceived English vowel more accurately than did the relatively inexperienced nonnative subject.
Journal ArticleDOI
Intelligibility of normal speech I: global and fine-grained acoustic-phonetic talker characteristics
TL;DR: It was found thattalkers with larger vowel spaces were generally more intelligible than talkers with reduced spaces, and a substantial portion of variability in normal speech intelligibility is traceable to specific acoustic-phonetic characteristics of the talker.
Patent
Knowledge-based speech recognition system and methods having frame length computed based upon estimated pitch period of vocalic intervals
Edward Komissarchik,Vladimir L. Arlazarov,Dimitri Bogdanov,Yuri Finkelstein,Andrei Ivanov,Jacob Kaminsky,Julia Komissarchik,Olga Krivnova,Mikhail Kronrod,Mikhail Malkovsky,Maxim Paklin,Alexander Rozanov,Vladimir Segal,Nina Zinovieva +13 more
TL;DR: In this article, a knowledge-based speech recognition apparatus and methods are provided for translating an input speech signal to text, which employ a largely speaker independent dictionary based upon the application of phonological and phonetic/acoustic rules to generate acoustic event transcriptions against which the series of hypothesized acoustic feature vectors are compared to select word choices.