| 1 |
Using heterogeneity in semi-supervised transcription hypotheses to improve code-switched speech recognition ...
|
|
|
|
Abstract:
Modeling code-switched speech is an important problem in automatic speech recognition (ASR). Labeled code-switched data are rare, so monolingual data are often used to model code-switched speech. These monolingual data may be more closely matched to one of the languages in the code-switch pair. We show that such asymmetry can bias prediction toward the better-matched language and degrade overall model performance. To address this issue, we propose a semi-supervised approach for code-switched ASR. We consider the case of English-Mandarin code-switching, and the problem of using monolingual data to build bilingual "transcription models'' for annotation of unlabeled code-switched data. We first build multiple transcription models so that their individual predictions are variously biased toward either English or Mandarin. We then combine these biased transcriptions using confidence-based selection. This strategy generates a superior transcript for semi-supervised training, and obtains a 19% relative improvement ... : 5 pages ...
|
|
Keyword:
Audio and Speech Processing eess.AS; Computation and Language cs.CL; FOS Computer and information sciences; FOS Electrical engineering, electronic engineering, information engineering; Sound cs.SD
|
|
URL: https://dx.doi.org/10.48550/arxiv.2106.07699
https://arxiv.org/abs/2106.07699
|
|
BASE
|
|
Hide details
|
|
|
| 3 |
Lexical speaker identification in TV shows
|
|
|
|
In: ISSN: 1380-7501 ; EISSN: 1573-7721 ; Multimedia Tools and Applications ; https://hal.archives-ouvertes.fr/hal-01690342 ; Multimedia Tools and Applications, Springer Verlag, 2015, 74 (4), pp.1377 - 1396. ⟨10.1007/s11042-014-1940-3⟩ (2015)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Comparing decoding strategies for subword-based keyword spotting in low-resourced languages
|
|
|
|
In: Annual Conference of the International Speech Communication Association ; https://hal.archives-ouvertes.fr/hal-01843408 ; Annual Conference of the International Speech Communication Association , ISCA, Sep 2014, Singapore, Singapore (2014)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Efficient Rule Scoring for Improved Grapheme-Based Lexicons
|
|
|
|
In: European Signal Processing Conference ; https://hal.archives-ouvertes.fr/hal-01843411 ; European Signal Processing Conference, Jan 2014, Lisbon, Portugal (2014)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Cross-Word Sub-Word Units for Low-Resource Keyword Spotting
|
|
|
|
In: International Workshop on Spoken Languages Technologies for Under-resourced languages ; https://hal.archives-ouvertes.fr/hal-01843415 ; International Workshop on Spoken Languages Technologies for Under-resourced languages, May 2014, St. Petersburg, Russia (2014)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Efficient Rule Scoring For Improved Grapheme-Based Lexicons ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Acoustic unit discovery and pronunciation generation from a grapheme-based lexicon
|
|
|
|
In: IEEE Automatic Speech Recognition and Understanding Workshop ; https://hal.archives-ouvertes.fr/hal-01843433 ; IEEE Automatic Speech Recognition and Understanding Workshop, Dec 2013, Olomouc, Czech Republic (2013)
|
|
BASE
|
|
Show details
|
|
|
|
|
