Improving 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 systems are a natural modeling choice due to their ease of use and superior performance in monolingual settings. However, it is well known that end-to-end systems require large amounts of labeled speech. In this work, we investigate improving code-switched ASR in low resource settings via data augmentation using code-switched text-to-speech (TTS) synthesis. We propose two targeted techniques to effectively leverage TTS speech samples: 1) Mixup, an existing technique to create new training samples via linear interpolation of existing samples, applied to TTS and real speech samples, and 2) a new loss function, used in conjunction with TTS samples, to encourage code-switched predictions. We report significant improvements in ASR performance achieving absolute word error rate (WER) reductions of up to 5%, and measurable improvement in code switching using our proposed techniques on a Hindi-English code-switched ASR task.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data Augmentationspeech-recognitionSpeech Recognitiontext-to-speechText to SpeechMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Improved Sentiment Detection via Label Transfer from Monolingual to Synthetic Code-Switched Text
Multilingual writers and speakers often alternate between two languages in a single discourse, a practice called "code-switching". Existing sentiment detection methods are usually trained on sentiment-labeled monolingual…
Hate Speech DetectionProgressive Sentiment Analysis for Code-Switched Text Data
Multilingual transformer language models have recently attracted much attention from researchers and are used in cross-lingual transfer learning for many NLP tasks such as text classification and named entity recognition…
Cross-Lingual Transfernamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+4CST5: Data Augmentation for Code-Switched Semantic Parsing
Extending semantic parsers to code-switched input has been a challenging problem, primarily due to a lack of supervised training data. In this work, we introduce CST5, a new data augmentation technique that finetunes a T…
Data AugmentationSemantic ParsingCST5: Data augmentation for Code-Switched Semantic Parsing
Extending semantic parsers to code-switched input has been a challenging problem, primarily due to lack of labeled data for supervision. In this work, we introduce CST5, a new data augmentation technique that finetunes …
Data AugmentationSemantic ParsingCS-FLEURS: A Massively Multilingual and Code-Switched Speech Dataset
We present CS-FLEURS, a new dataset for developing and evaluating code-switched speech recognition and translation systems beyond high-resourced languages. CS-FLEURS consists of 4 test sets which cover in total 113 uniqu…
Speech Recognition