Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 2 de 2
Filtrar
Mais filtros










Base de dados
Intervalo de ano de publicação
1.
Sensors (Basel) ; 21(9)2021 Apr 28.
Artigo em Inglês | MEDLINE | ID: mdl-33924798

RESUMO

With the rapid development of speech assistants, adapting server-intended automatic speech recognition (ASR) solutions to a direct device has become crucial. For on-device speech recognition tasks, researchers and industry prefer end-to-end ASR systems as they can be made resource-efficient while maintaining a higher quality compared to hybrid systems. However, building end-to-end models requires a significant amount of speech data. Personalization, which is mainly handling out-of-vocabulary (OOV) words, is another challenging task associated with speech assistants. In this work, we consider building an effective end-to-end ASR system in low-resource setups with a high OOV rate, embodied in Babel Turkish and Babel Georgian tasks. We propose a method of dynamic acoustic unit augmentation based on the Byte Pair Encoding with dropout (BPE-dropout) technique. The method non-deterministically tokenizes utterances to extend the token's contexts and to regularize their distribution for the model's recognition of unseen words. It also reduces the need for optimal subword vocabulary size search. The technique provides a steady improvement in regular and personalized (OOV-oriented) speech recognition tasks (at least 6% relative word error rate (WER) and 25% relative F-score) at no additional computational cost. Owing to the BPE-dropout use, our monolingual Turkish Conformer has achieved a competitive result with 22.2% character error rate (CER) and 38.9% WER, which is close to the best published multilingual system.


Assuntos
Percepção da Fala , Fala , Acústica , Interface para o Reconhecimento da Fala , Vocabulário
2.
Opt Express ; 29(2): 1722-1735, 2021 Jan 18.
Artigo em Inglês | MEDLINE | ID: mdl-33726380

RESUMO

Prospects for average power scaling of sub-MW output peak power picosecond fiber lasers by utilization of a Yb-doped tapered fiber at the final amplification stage were studied. In this paper, it was shown experimentally that a tapered fiber allows the achievement of an average power level of 150 W (limited by the available pump power) with a peak power of 0.74 MW for 22 ps pulses with no signs of transverse mode instability. Measurements of the mode content using the S2 technique showed a negligible level of high order modes (less than 0.3%) in the output radiation even for the maximum output power level. Our reliability tests predict no thermal issues during long-term operation (105 hours) of the developed tapered fiber laser up to kilowatt output average power levels.

SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...