Uneven success: automatic speech recognition and ethnicity-related dialects
نویسندگان
چکیده
Addressing racial bias in automatic speech recognition is an area of concern fields associated with human-computer interaction. Research to date suggests that sociolinguistic variation, namely systematic sources sociophonetic has yet be extensively exploited acoustic model architectures. This paper reports a study evaluates the performance one ASR system for multi-ethnic sample speakers from American Pacific Northwest (including Native American, African European and ChicanX speakers). Using approach characterizing vocalic consonantal we ask which dialect features appear most challenging our system. We also error types are particular four ethnic dialects sampled. Recordings both conversational read were coded common set 18 variables distinct phonetic profiles. Automatic transcription was achieved using CLOx, custom-built created analysis. Normalized frequency rates compared across samples evaluate CLOx performance. Nf demonstrate clear differential system, pointing output. Specific predictions made regarding approaches might taken leverage knowledge improve social dialect-recognition accuracy systems.
منابع مشابه
A Database for Automatic Persian Speech Emotion Recognition: Collection, Processing and Evaluation
Abstract Recent developments in robotics automation have motivated researchers to improve the efficiency of interactive systems by making a natural man-machine interaction. Since speech is the most popular method of communication, recognizing human emotions from speech signal becomes a challenging research topic known as Speech Emotion Recognition (SER). In this study, we propose a Persian em...
متن کاملPhonotactic Recognition of Greek and Cypriot Dialects from Telephone Speech
In the present work we report recent progress in development of dialect recognition system for the Standard Modern Greek and Cypriot dialect of Greek language. Specifically, we rely on a compound recognition scheme, where the outputs of multiple phone recognizers, trained on different European languages are combined. This allows achieving higher recognition accuracy, when compared to the one of...
متن کاملLanguage Recognition for Dialects and Closely Related Languages
This paper describes our development work to design a language recognition system that can discriminate closely related languages and dialects of the same language. The work was a joint effort by LIMSI and Vocapia Research in preparation for the NIST 2015 Language Recognition Evaluation (LRE). The language recognition system results from a fusion of four core classifiers: a phonotactic componen...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Speech Communication
سال: 2022
ISSN: ['1872-7182', '0167-6393']
DOI: https://doi.org/10.1016/j.specom.2022.03.009