1 |
Finding Concept-specific Biases in Form--Meaning Associations ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Finding Concept-specific Biases in Form–Meaning Associations ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Disambiguatory Signals are Stronger in Word-initial Positions ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Finding Concept-specific Biases in Form–Meaning Associations
|
|
|
|
In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2021)
|
|
BASE
|
|
Show details
|
|
5 |
Disambiguatory Signals are Stronger in Word-initial Positions
|
|
|
|
In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume (2021)
|
|
BASE
|
|
Show details
|
|
6 |
Disambiguatory Signals are Stronger in Word-initial Positions ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Finding Concept-specific Biases in Form--Meaning Associations ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Language-agnostic Multilingual Modeling ...
|
|
|
|
Abstract:
Multilingual Automated Speech Recognition (ASR) systems allow for the joint training of data-rich and data-scarce languages in a single model. This enables data and parameter sharing across languages, which is especially beneficial for the data-scarce languages. However, most state-of-the-art multilingual models require the encoding of language information and therefore are not as flexible or scalable when expanding to newer languages. Language-independent multilingual models help to address this issue, and are also better suited for multicultural societies where several languages are frequently used together (but often rendered with different writing systems). In this paper, we propose a new approach to building a language-agnostic multilingual ASR system which transforms all languages to one writing system through a many-to-one transliteration transducer. Thus, similar sounding acoustics are mapped to a single, canonical target sequence of graphemes, effectively separating the modeling and rendering ...
|
|
Keyword:
Audio and Speech Processing eess.AS; FOS Computer and information sciences; FOS Electrical engineering, electronic engineering, information engineering; Machine Learning stat.ML; Sound cs.SD
|
|
URL: https://arxiv.org/abs/2004.09571 https://dx.doi.org/10.48550/arxiv.2004.09571
|
|
BASE
|
|
Hide details
|
|
11 |
Processing South Asian Languages Written in the Latin Script: the Dakshina Dataset ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Phonotactic Complexity and Its Trade-offs
|
|
|
|
In: Transactions of the Association for Computational Linguistics, 8 (2020)
|
|
BASE
|
|
Show details
|
|
13 |
Explaining vowel inventory tendencies via simulation: finding a role for quantal locations and formant normalization
|
|
|
|
In: North East Linguistics Society (2020)
|
|
BASE
|
|
Show details
|
|
14 |
Are All Languages Equally Hard to Language-Model?
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2019)
|
|
BASE
|
|
Show details
|
|
15 |
Rethinking Phonotactic Complexity
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2019)
|
|
BASE
|
|
Show details
|
|
17 |
Graph-Based Word Alignment for Clinical Language Evaluation
|
|
|
|
In: Comput Linguist Assoc Comput Linguist (2015)
|
|
BASE
|
|
Show details
|
|
18 |
COMPUTATIONAL ANALYSIS OF TRAJECTORIES OF LINGUISTIC DEVELOPMENT IN AUTISM
|
|
|
|
BASE
|
|
Show details
|
|
|
|