Bridging the Gap between Linguists and Technology Developers: Large-Scale, Sociolinguistic Annotation for Dialect and Speaker Recognition

نویسندگان

  • Christopher Cieri
  • Stephanie Strassel
  • Meghan Lammie Glenn
  • Reva Schwartz
  • Wade Shen
  • Joseph P. Campbell
چکیده

Recent years have seen increased interest within the speaker recognition community in high-level features including, for example, lexical choice, idiomatic expressions or syntactic structures. The promise of speaker recognition in forensic applications drives development toward systems robust to channel differences by selecting features inherently robust to channel difference. Within the language recognition community, there is growing interest in differentiating not only languages but also mutually intelligible dialects of a single language. Decades of research in dialectology suggest that high-level features can enable systems to cluster speakers according to the dialects they speak. The Phanotics (Phonetic Annotation of Typicality in Conversational Speech) project seeks to identify high-level features characteristic of American dialects, annotate a corpus for these features, use the data to dialect recognition systems and also use the categorization to create better models for speaker recognition. The data, once published, should be useful to other developers of speaker and dialect recognition systems and to dialectologists and sociolinguists. We expect the methods will generalize well beyond the speakers, dialects, and languages discussed here and should, if successful, provide a model for how linguists and technology developers can collaborate in the future for the benefit of both groups and toward a deeper understanding of how languages vary and change.

برای دانلود 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

Prolegomenon for an analysis of dialect coding conventions for data sharing1

Introduction For the past two decades, the Linguistic Data Consortium at the University of Pennsylvania has fostered the intersection of linguistics and language technologies, building and sharing datasets for use in language related sub-disciplines. Over that time, we have observed a gradual convergence of desiderata and, to a lesser extent, methodologies. Speech technology developers who have...

متن کامل

Effective Factors on Naming Practices in Iran: Sociopolitics or Dialect?

Naming as an inseparable sign of a country’s language has attracted the attention of many linguists to formulate and test hypotheses regarding the culture and language of the people of a certain area. Iran appears like a proper destination for conducting a research focusing on naming based on several factors such as geography or chronology. The present article aims to take a specific look at th...

متن کامل

شبکه عصبی پیچشی با پنجره‌های قابل تطبیق برای بازشناسی گفتار

Although, speech recognition systems are widely used and their accuracies are continuously increased, there is a considerable performance gap between their accuracies and human recognition ability. This is partially due to high speaker variations in speech signal. Deep neural networks are among the best tools for acoustic modeling. Recently, using hybrid deep neural network and hidden Markov mo...

متن کامل

-

The development and evolution of any system–person, organization–nation depends on how the system succeeds to bridge the gap between what the system knows and what the system does (with the knowledge). We call this the gap between knowing and doing or the knowing-doing gap. If the system does not do what it knows, it will lose out in competition with other systems, its relative performance in...

متن کامل

Speaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation

A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...

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

برای دانلود 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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2008