Multilingual speech recognition and identification

Multilingual Query-by-Example Keyword Spotting with Metric Learning and Phoneme-to-Embedding Mapping

Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities

Multilingual Word Error Rate Estimation: e-WER3

TOWARDS ZERO-SHOT CODE-SWITCHED SPEECH RECOGNITION

Improving Massively Multilingual ASR With Auxiliary CTC Objectives

TEXTLESS DIRECT SPEECH-TO-SPEECH TRANSLATION WITH DISCRETE SPEECH REPRESENTATION

Multilingual end-to-end spoken language understanding for ultra-low footprint applications

Joint Training And Decoding for Multilingual End-to-End Simultaneous Speech Translation

UML: A Universal Monolingual Output Layer for Multilingual ASR

Code-Switching Text Generation and Injection in Mandarin-English ASR

Exploring universal singing speech language identification using self-supervised learning based front-end features

Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in Automatic Speech Recognition