Native vs. non-native accent identification using Japanese spoken telephone numbers

Amino, Kanae; Osanai, Takashi

doi:10.1016/j.specom.2013.07.010

Cited by 10 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fig. 1 illustrates how phone number strings are realized in Tokyo Japanese, conforming to its particular prosodic structure, known as a bipodic template (Amino and Osanai [2]). The line in Fig.…”

Section: Datamentioning

confidence: 99%

Dataset of focus prosody in Japanese phone numbers

2019

View full text Add to dashboard Cite

The data in this article present position-dependent variation of focus prosody within phone number strings in Tokyo Japanese. Four acoustic parameters (duration, mean intensity, maximum pitch, and time-normalized pitch contours) are reported to illustrate focus prosody of Japanese phone numbers, separately for broad focus and corrective focus. The data also include four attached files: 1) time-normalized pitch contours for all speakers (Appendix A), 2) aggregated data of duration, mean intensity, and maximum pitch for on-focus effects (Appendix B), 3) a Python script automatically generating target stimuli (Appendix C), and 4) target stimuli used for each focus type (Appendix D). The data set can be used for several research projects including speech recognition, focus study, speaker variation in marking prosodic focus, and prosody modeling in Tokyo Japanese. Detailed discussion of data interpretation can be found in the article entitled “Prosodic focus of telephone numbers in Tokyo Japanese” (Lee et al.).

show abstract

Section: Datamentioning

confidence: 99%

Dataset of focus prosody in Japanese phone numbers

2019

View full text Add to dashboard Cite

show abstract

“…That is why, we consider in this study "accent" as the speech properties that cover a small group of variations which could occur in a certain language, unlike the dialects which refer to significant variations in the same language [2]. This definition refers also, to "accent" as the speech properties that indicate which part of a country the speaker originates from [6].…”

Section: Related Workmentioning

confidence: 99%

“…The first class deals with the identification of native and non-native speakers based on the sound of their speech [6][4] [8]. Developing an automatic system to identify speakers as native or non-native, as well as their native language, is an important aspect for the purpose of reducing the impact of non-native speech on languages recognition systems [8], to provide a critical piece of information in making decisions for security purposes [9], or also to be used by forensic scientists as part of their assessment of the speaker's identity [6].…”

Section: Related Workmentioning

confidence: 99%

“…Moreover, it can be helpful for forensic speaker profiling in judicial or military situation [5]. Identifying the speaker's accent, his/her nationality and/or hometown, can often lead to important clues with regard to the suspect [6]. The more realistic example for these forensic applications is the American journalist case, when several British and American newspapers have reported that the identity of James Foley's killer is established by combining intelligence services investigations with different forensic techniques, like voice and accent recognition, video and images analysis and Internet traces examination [7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Regional accents recognition based on i-vectors approach: The case of the Algerian linguistic environment

Djellab

Amrouche

Mehallegue³

et al. 2015

2015 4th International Conference on Electrical Engineering (ICEE)

View full text Add to dashboard Cite

Regional accents recognition is one of the most important research topics in speech processing. However, the development of such systems is time-consuming and an expensive process since it requires collecting and processing a large amount of training and evaluation data for each target accent. This work presents some preliminary results about the Algerian regional accents recognition using the i-vectors approach. The experiments have been carried out using a dataset collected from the east and the center of Algeria. The obtained results show the benefits of using the i-vectors approach to recognize both regional accents and to assess the impact of evaluation data quality on the accuracy of the proposed recognition method. However, it has been noted that the confusion rates obtained between both accents may be related to the evaluation data quality, the linguistic similarity existing between both accents and some languages contact phenomenon such as the code switching.

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

Native vs. non-native accent identification using Japanese spoken telephone numbers

Cited by 10 publications

References 28 publications

Dataset of focus prosody in Japanese phone numbers

Dataset of focus prosody in Japanese phone numbers

Regional accents recognition based on i-vectors approach: The case of the Algerian linguistic environment

Accent rating by native and non-native listeners

Contact Info

Product

Resources

About