Instance-Based Model Adaptation For Direct Speech Translation
Despite recent technology advancements, the effectiveness of neural approaches to end-to-end speech-to-text translation is still limited by the paucity of publicly available training corpora. We tackle this limitation with a method to improve data exploitation and boost the system's performance at inference time. Our approach allows us to customize "on the fly" an existing model to each incoming translation request. At its core, it exploits an instance selection procedure to retrieve, from a given pool of data, a small set of samples similar to the input query in terms of latent properties of its audio signal. The retrieved samples are then used for an instance-specific fine-tuning of the model. We evaluate our approach in three different scenarios. In all data conditions (different languages, in/out-of-domain adaptation), our instance-based adaptation yields coherent performance gains over static models.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationSpeech-to-TextSpeech-to-Text TranslationTranslationSimilar Papers 제목 키워드 기반
Neural Speech Translation at AppTek
This work describes AppTek’s speech translation pipeline that includes strong state-of-the-art automatic speech recognition (ASR) and neural machine translation (NMT) components. We show how these components can be tight…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine TranslationNMT+3English-Indonesian Neural Machine Translation for Spoken Language Domains
In this work, we conduct a study on Neural Machine Translation (NMT) for English-Indonesian (EN-ID) and Indonesian-English (ID-EN). We focus on spoken language domains, namely colloquial and speech languages. We build NM…
Domain AdaptationMachine TranslationNMTTranslationInstance Weighting for Neural Machine Translation Domain Adaptation
Instance weighting has been widely applied to phrase-based machine translation domain adaptation. However, it is challenging to be applied to Neural Machine Translation (NMT) directly, because NMT is not a linear model. …
Domain AdaptationMachine TranslationNMTSentence+1Non-Parametric Domain Adaptation for End-to-End Speech Translation
The end-to-end speech translation (E2E-ST) has received increasing attention due to the potential of its less error propagation, lower latency, and fewer parameters. However, the effectiveness of neural-based approaches …
Domain AdaptationTranslationTripletNon-Parametric Domain Adaptation for End-to-End Speech Translation
End-to-End Speech Translation (E2E-ST) has received increasing attention due to the potential of its less error propagation, lower latency, and fewer parameters. However, the effectiveness of neural-based approaches to t…
Domain AdaptationTranslationTriplet