1 |
Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Analyzing the Effects of Reasoning Types on Cross-Lingual Transfer Performance ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Designing Language Technologies for Social Good: The Road not Taken ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Use of Formal Ethical Reviews in {NLP} Literature: {H}istorical Trends and Current Practices ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
A New Dataset for Natural Language Inference from Code-mixed Conversations ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
The State and Fate of Linguistic Diversity and Inclusion in the NLP World ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Phone Merging for Code-switched Speech Recognition
|
|
|
|
In: Third Workshop on Computational Approaches to Linguistic Code-switching ; https://hal.inria.fr/hal-01800466 ; Third Workshop on Computational Approaches to Linguistic Code-switching, collocated with ACL 2018 Jul 2018, Melbourne, Australia (2018)
|
|
Abstract:
International audience ; Speakers in multilingual communities often switch between or mix multiple languages in the same conversation. Automatic Speech Recognition (ASR) of code-switched speech faces many challenges including the influence of phones of different languages on each other. This paper shows evidence that phone sharing between languages improves the Acoustic Model performance for Hindi-English code-switched speech. We compare base-line system built with separate phones for Hindi and English with systems where the phones were manually merged based on linguistic knowledge. Encouraged by the improved ASR performance after manually merging the phones, we further investigate multiple data-driven methods to identify phones to be merged across the languages. We show detailed analysis of automatic phone merging in this language pair and the impact it has on individual phone accuracies and WER. Though the best performance gain of 1.2% WER was observed with manually merged phones, we show experimentally that the manual phone merge is not optimal.
|
|
Keyword:
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]; [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD]; Code switching; Speech recognigntion
|
|
URL: https://hal.inria.fr/hal-01800466 https://hal.inria.fr/hal-01800466/document https://hal.inria.fr/hal-01800466/file/phone-merging-acl.pdf
|
|
BASE
|
|
Hide details
|
|
14 |
Is this word borrowed? An automatic approach to quantify the likeliness of borrowing in social media ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|