Meta-Transfer Learning for Code-Switched Speech Recognition
An increasing number of people in the world today speak a mixed-language as a result of being multilingual. However, building a speech recognition system for code-switching remains difficult due to the availability of limited resources and the expense and significant effort required to collect mixed-language data. We therefore propose a new learning method, meta-transfer learning, to transfer learn on a code-switched speech recognition system in a low-resource setting by judiciously extracting information from high-resource monolingual datasets. Our model learns to recognize individual languages, and transfer them so as to better recognize mixed-language speech by conditioning the optimization on the code-switching data. Based on experimental results, our model outperforms existing baselines on speech recognition and language modeling tasks, and is faster to converge.
Code (1)
Tasks
Language ModelingLanguage Modellingspeech-recognitionSpeech RecognitionTransfer LearningSimilar Papers 제목 키워드 기반
Learning not to Discriminate: Task Agnostic Learning for Improving Monolingual and Code-switched Speech Recognition
Recognizing code-switched speech is challenging for Automatic Speech Recognition (ASR) for a variety of reasons, including the lack of code-switched training data. Recently, we showed that monolingual ASR systems fine-tu…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionLearning to Recognize Code-switched Speech Without Forgetting Monolingual Speech Recognition
Recently, there has been significant progress made in Automatic Speech Recognition (ASR) of code-switched speech, leading to gains in accuracy on code-switched datasets in many language pairs. Code-switched speech co-occ…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionMultilingual Bottleneck Features for Improving ASR Performance of Code-Switched Speech in Under-Resourced Languages
In this work, we explore the benefits of using multilingual bottleneck features (mBNF) in acoustic modelling for the automatic speech recognition of code-switched (CS) speech in African languages. The unavailability of a…
Acoustic ModellingAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognition+1Using heterogeneity in semi-supervised transcription hypotheses to improve code-switched speech recognition
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 m…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionImproving Low Resource Code-switched ASR using Augmented Code-switched TTS
Building Automatic Speech Recognition (ASR) systems for code-switched speech has recently gained renewed attention due to the widespread use of speech technologies in multilingual communities worldwide. End-to-end ASR sy…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data Augmentationspeech-recognition+3