Hypothesis-driven accent discrimination
نویسنده
چکیده
Native and non-native use of language differs, depending on the proficiency of the speaker, in clear and quantifiable ways. It has been shown that customizing the acoustic and language models of a natural language understanding system can significantly improve handling of non-native input; in order to make such a switch, however, the nativeness status of the user must be known. In this paper, we show how the recognition hypothesis can be used to predict with very high accuracy whether the speaker is native. Effectiveness of both word-based and phone-based classification are evaluated, and a discussion of the primary discriminative features is presented. In an LVCSR system in which users are both native and non-native, we have achieved a 15.6% relative decrease in word error rate by integrating this classification method with speech recognition.
منابع مشابه
Perception of Nonnative Accent: A Cross-Sectional Perspective Pilot Survey
Accent bias is a consequence of ethnocentrism. No studies have examined accent bias across educational levels in the U.S., much less across students and professionals in speech language pathology (SLP), a field that requires multicultural sensitivity training. This study examines nonnative accent perception among three groups—high schoolers, SLP students, and SLP professionals. One-hundred-and-...
متن کاملPerception of Lexical Pitch Accent by Kyungsang and Cholla Korean Listeners
This paper investigates the identification and discrimination of lexical pitch accent by native and non-native dialectal listeners. Specifically, this research is focused on examining the relation between linguistic experience and phonetic levels of discrimination in speech perception. Participants identified and discriminated the continuum resynthesized from three pitch accent minimal pairs of...
متن کاملAutomatic accent classification of foreign accented australian English speech
English speech based on accent dependent parallel phoneme recognition (PPR) has been developed. The classifier is designed to process continuous speech and to discriminate between native Australian English (AuE) speakers and two migrant speaker groups with foreign accents, whose first languages are Lebanese Arabic (LA) and South Vietnamese (SV). The training of the system can be automated and i...
متن کاملRapid Adaptation of Foreign-Accented HMM-Based Speech Synthesis
This paper presents findings of listeners’ perception of speaker identity in synthetic speech. Specifically, we investigated what the effect is on the perceived identity of a speaker when using differently accented average voice models and limited amounts (five and fifteen sentences) of a speaker’s data to create the synthetic stimuli. A speaker discrimination task was used to measure speaker i...
متن کاملEigen-channel compensation and discriminatively trained Gaussian mixture models for dialect and accent recognition
This paper presents a series of dialect/accent identification results for three sets of dialects with discriminatively trained Gaussian mixture models and feature compensation using eigen-channel decomposition. The classification tasks evaluated in the paper include: 1) the Chinese language classes, 2) American and Indian accented English and 3) discrimination between three Arabic dialects. The...
متن کامل