paper-with-me

Papers

Code-Switching without Switching: Language Agnostic End-to-End Speech Translation

2022-10-04 · Christian Huber, Enes Yavuz Ugan, Alexander Waibel

We propose a) a Language Agnostic end-to-end Speech Translation model (LAST), and b) a data augmentation strategy to increase code-switching (CS) performance. With increasing globalization, multiple languages are increasingly used interchangeably during fluent speech. Such CS complicates traditional speech recognition and translation, as we must recognize which language was spoken first and then apply a language-dependent recognizer and subsequent translation component to generate the desired target language output. Such a pipeline introduces latency and errors. In this paper, we eliminate the need for that, by treating speech recognition and translation as one unified end-to-end speech translation problem. By training LAST with both input languages, we decode speech into one target language, regardless of the input language. LAST delivers comparable recognition and speech translation accuracy in monolingual usage, while reducing latency and error rate considerably when CS is observed.

📄 PDF Abstract BibTeX arXiv:2210.01512

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentationspeech-recognitionSpeech RecognitionTranslation

Similar Papers 제목 키워드 기반

Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation

2018-11-06 · Ching-Ting Chang, Shun-Po Chuang, Hung-Yi Lee

Code-switching is about dealing with alternative languages in speech or text. It is partially speaker-depend and domain-related, so completely explaining the phenomenon by linguistic rules is challenging. Compared to mos…

Data AugmentationGenerative Adversarial NetworkSentence

Hierarchical Meta-Embeddings for Code-Switching Named Entity Recognition

2019-09-18 · IJCNLP 2019 11 · Genta Indra Winata, Zhaojiang Lin, Jamin Shin, Zihan Liu 외

In countries that speak multiple main languages, mixing up different languages within a conversation is commonly called code-switching. Previous works addressing this challenge mainly focused on word-level aspects such a…

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Word Embeddings

Optimizing Bilingual Neural Transducer with Synthetic Code-switching Text Generation

2022-10-21 · Thien Nguyen, Nathalie Tran, Liuhui Deng, Thiago Fraga da Silva 외

Code-switching describes the practice of using more than one language in the same sentence. In this study, we investigate how to optimize a neural transducer based bilingual automatic speech recognition (ASR) model for c…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Sentencespeech-recognition+2

Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling

2021-04-13 · Genta Indra Winata

In this thesis, we address the data scarcity and limitations of linguistic theory by proposing language-agnostic multi-task training methods. First, we introduce a meta-learning-based approach, meta-transfer learning, in…

Data AugmentationLanguage ModellingMeta-LearningMulti-Task Learning+1

Reducing language context confusion for end-to-end code-switching automatic speech recognition

2022-01-28 · Shuai Zhang, Jiangyan Yi, Zhengkun Tian, JianHua Tao 외

Code-switching deals with alternative languages in communication process. Training end-to-end (E2E) automatic speech recognition (ASR) systems for code-switching is especially challenging as code-switching training data …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Sentencespeech-recognition+1