Improving Sub-Phone Modeling for Better Native Language Identification with Non-Native English Speech

نویسندگان

  • Yao Qian
  • Keelan Evanini
  • Xinhao Wang
  • David Suendermann-Oeft
  • Robert A. Pugh
  • Patrick L. Lange
  • Hillary R. Molloy
  • Frank K. Soong
چکیده

Identifying a speaker’s native language with his speech in a second language is useful for many human-machine voice interface applications. In this paper, we use a sub-phone-based i-vector approach to identify non-native English speakers’ native languages by their English speech input. Time delay deep neural networks (TDNN) are trained on LVCSR corpora for improving the alignment of speech utterances with their corresponding sub-phonemic “senone” sequences. The phonetic variability caused by a speaker’s native language can be better modeled with the sub-phone models than the conventional phone model based approach. Experimental results on the database released for the 2016 Interspeech ComParE Native Language challenge with 11 different L1s show that our system outperforms the best system by a large margin (87.2% UAR compared to 81.3% UAR for the best system from the 2016 ComParE challenge).

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Automatic accentedness evaluation of non-native speech using phonetic and sub-phonetic posterior probabilities

Automatic evaluation of non-native speech accentedness has potential implications for not only language learning and accent identification systems but also for speaker and speech recognition systems. From the perspective of speech production, the two primary factors influencing the accentedness are the phonetic and prosodic structure. In this paper, we propose an approach for automatic accented...

متن کامل

English vowel identification in quiet and noise: effects of listeners' native language background

PURPOSE To investigate the effect of listener's native language (L1) and the types of noise on English vowel identification in noise. METHOD Identification of 12 English vowels was measured in quiet and in long-term speech-shaped noise and multi-talker babble (MTB) noise for English- (EN), Chinese- (CN) and Korean-native (KN) listeners at various signal-to-noise ratios (SNRs). RESULTS Compa...

متن کامل

Non-native English Speaking Teachers’ Pragmatic Criteria in the Holistic and Analytic Rating of the Agreement Speech Act Productions of Iranian EFL Learners

Pragmatic rating is considered as one of the novel and crucial aspects of second language education which has not been maneuvered upon in the literature. To address this gap, the current study aimed to inspect the matches and mismatches, to explore rating variations, and to assess the rater consistency between the holistic and analytic rating methods of the speech act of agreement in L2 by non-...

متن کامل

Unsupervised acoustic model adaptation for multi-origin non native ASR

To date, the performance of speech and language recognition systems is poor on non-native speech. The challenge for nonnative speech recognition is to maximize the accuracy of a speech recognition system when only a small amount of nonnative data is available. We report on the acoustic model adaptation for improving the recognition of non-native speech in English, French and Vietnamese, spoken ...

متن کامل

Speech-like Pragmatic Markers in Argumentative Essays Written by Iranian EFL Students and Native English Speaking Students

In this study, the use of speech-like pragmatic markers in Iranian EFL students’ academic writing was investigated. Speech-like pragmatic markers, such as I think, well, I guess, actually, anyway, anyhow, etc. are linguistic components that are more specific to conversation than writing, and writers may wrongly include them in their academic writing. To examine the students’ use of speech-like ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017