Massively Multilingual Adversarial Speech Recognition

Abstract

We report on adaptation of multilingual end-to-end speech recognition models trained on as many as 100 languages. Our findings shed light on the relative importance of similarity between the target and pretraining languages along the dimensions of phonetics, phonology, language family, geographical location, and orthography. In this context, experiments demonstrate the effectiveness of two additional pretraining objectives in encouraging language-independent encoder representations: a context-independent phoneme objective paired with a language-adversarial classification objective.

Stats

• citations38
• S2 citations—
• github stars0
• HF likes0
• heat score11.93
• arxiv keyadams2019massively

Related papers

• Improved Self-supervised Multilingual Speech Representation Learning Combined With Auxiliary Language Information (2022)0.00
• Adapt-and-adjust: Overcoming The Long-tail Problem Of Multilingual Speech Recognition (2020)10.35
• Multilingual Speech Recognition With A Single End-to-end Model (2017)16.05
• Multi-staged Cross-lingual Acoustic Model Adaption For Robust Speech Recognition In Real-world Applications -- A Case Study On German Oral History Interviews (2020)0.00
• Large-scale Multilingual Speech Recognition With A Streaming End-to-end Model (2019)14.97
• Speaker Verification Using End-to-end Adversarial Language Adaptation (2018)11.19
• Language-universal Adapter Learning With Knowledge Distillation For End-to-end Multilingual Speech Recognition (2023)0.95
• Investigating The Impact Of Cross-lingual Acoustic-phonetic Similarities On Multilingual Speech Recognition (2022)3.58