Scaling speech technology to 1,000+ languages

V Pratap, A Tjandra, B Shi, P Tomasello, A Babu… - Journal of Machine …, 2024 - jmlr.org
Expanding the language coverage of speech technology has the potential to improve
access to information for many more people. However, current speech technology is …

Scaling end-to-end models for large-scale multilingual asr

B Li, R Pang, TN Sainath, A Gulati… - 2021 IEEE Automatic …, 2021 - ieeexplore.ieee.org
Building ASR models across many languages is a challenging multi-task learning problem
due to large variations and heavily unbalanced data. Existing work has shown positive …

Language-independent and language-adaptive acoustic modeling for speech recognition

T Schultz, A Waibel - Speech Communication, 2001 - Elsevier
With the distribution of speech technology products all over the world, the portability to new
target languages becomes a practical concern. As a consequence our research focuses on …

Storing and reading information in mixtures of fluorescent molecules

AA Nagarkar, SE Root, MJ Fink, AS Ten… - ACS Central …, 2021 - ACS Publications
The rapidly increasing use of digital technologies requires the rethinking of methods to store
data. This work shows that digital data can be stored in mixtures of fluorescent dye …

A vector space modeling approach to spoken language identification

H Li, B Ma, CH Lee - IEEE Transactions on Audio, Speech, and …, 2006 - ieeexplore.ieee.org
We propose a novel approach to automatic spoken language identification (LID) based on
vector space modeling (VSM). It is assumed that the overall sound characteristics of all …

Recognizing speech of goats, wolves, sheep and… non-natives

D Van Compernolle - Speech Communication, 2001 - Elsevier
This paper reviews the current understanding of acoustic–phonetic issues and the problems
arising when trying to recognize speech from non-native speakers. Conceptually, regional …

[图书][B] Multilingual speech processing

T Schultz, K Kirchhoff - 2006 - books.google.com
Tanja Schultz and Katrin Kirchhoff have compiled a comprehensive overview of speech
processing from a multilingual perspective. By taking this all-inclusive approach to speech …

Improving the intelligibility of dysarthric speech

AB Kain, JP Hosom, X Niu, JPH Van Santen… - Speech …, 2007 - Elsevier
Dysarthria is a speech motor disorder usually resulting in a substantive decrease in speech
intelligibility by the general population. In this study, we have significantly improved the …

Multi-level annotation in the Emu speech database management system

S Cassidy, J Harrington - Speech communication, 2001 - Elsevier
Researchers in various fields, from acoustic phonetics to child language development, rely
on digitised collections of spoken language data as raw material for research. Access to this …

Multilingual phone models for vocabulary-independent speech recognition tasks

J Köhler - Speech Communication, 2001 - Elsevier
This paper presents three different methods for developing multilingual phone models for
flexible speech recognition tasks. The main goal of our investigations is to find multilingual …