Code-Switching (CS) remains a challenge for Automatic Speech Recognition (ASR), especially character-based models. With the combined choice of characters from multiple languages, the out-come from character-based models suffers from phoneme duplication, resulting in language-inconsistent spellings. We ...
本文中,作者提出一种简单高效的自监督方法Self-Augmented Language Transfer (SALT)使用code switching做augmentation,并采用了embedding mixup,无需任何其他数据,仅在英语数据上进行训练,就能够大大提升多语言模型在XNLI任务和PAWS-X任务(paraphrase identification)上的表现。 SALT的训练过程分为两个部分,第一个部分是offl...
Multi-Encoder-Decoder Transformer for Code-Switching Speech Recognition 主要从code switch的角度看待这篇文章,对TTS有所启发。 1 背景 在许多国家中,多语言是混合使用的。但是绝大多数的ASR模型,被设计为单语种服务,涉及到多语言的情况,效果不佳。 2详细设计 模型为Transformer -based model,最主要的设计为multi...
Project, a code-switching (CS) automatic speech recognition (ASR) system for Frisian-Dutch speech is developed that can accurately transcribe the local broadcaster's bilingual archives with CS speech. This archive contains recordings with monolingual Frisian and Dutch speech segments as well as ...
In code-switching, multiple languages are freely interchanged within a single sentence or between sentences. The success of low-resource multilingual and code-switching ASR often depends on the variety of languages in terms of their acoustics, linguistic characteristics as ...
Sunayana Sitaram, Kalika Bali, Monojit Choudhury Workshop on Computational Approaches to Linguistic Code Switching, 2018|July 2018 下载BibTex Speakers in multilingual communities often switch between or mix multiple languages in the same conversation. Automatic Speech Recognition (ASR) of codeswitched spe...
In this paper, we describe several techniques for improving the acoustic and language model of an automatic speech recognition (ASR) system operating on code-switching (CS) speech. We focus on the recognition of Frisian-Dutch radio broadcasts where one of the mixed languages, namely Frisian, is...
The application converts spoken Tamil and Vietnamese to text without auto-correction, code-mixing or code-switching. This paper proposed a complete web application, which, when perfected, could be used to act as a teaching tool to encourage correct pronunciation of syllables and words for ...
Further, the model has been trained on a synthetic code-switched set, hence the model performance might degrade on some out of domain code-switching cases. References [1] Google Sentencepiece Tokenizer [2] Conformer: Convolution-augmented Transformer for Speech Recognition [3] NVIDIA NeMo Toolkit ...
Code-switching Usually between speakers of equal fluency in two languages Casual speech/text Face-to-face or in social media Often defined in terms of a matrix language (based language word order) (major) Word order in matrix languages, as are particles (morphology) ...