Rapid Language Adaptation For Multilingual E2E Speech Recognition Using Encoder Prompting

Abstract

End-to-end multilingual speech recognition models handle multiple languages through a single model, often incorporating language identification to automatically detect the language of incoming speech. Since the common scenario is where the language is already known, these models can perform as language-specific by using language information as prompts, which is particularly beneficial for attention-based encoder-decoder architectures. However, the Connectionist Temporal Classification (CTC) approach, which enhances recognition via joint decoding and multi-task training, does not normally incorporate language prompts due to its conditionally independent output tokens. To overcome this, we introduce an encoder prompting technique within the self-conditioned CTC framework, enabling language-specific adaptation of the CTC model in a zero-shot manner. Our method has shown to significantly reduce errors by 28% on average and by 41% on low-resource languages.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykashiwagi2024rapid

Related papers

• Sequence-based Multi-lingual Low Resource Speech Recognition (2018)12.40
• Enhancing Multilingual Speech Recognition Through Language Prompt Tuning And Frame-level Language Adapter (2023)0.00
• Chain-of-thought Prompting For Speech Translation (2024)6.34
• Large-scale Multilingual Speech Recognition With A Streaming End-to-end Model (2019)14.97
• Massively Multilingual Adversarial Speech Recognition (2019)11.93
• Joint Ctc-attention Based End-to-end Speech Recognition Using Multi-task Learning (2016)20.43
• Speaker Adaptation For End-to-end CTC Models (2019)8.60
• Multilingual Training And Cross-lingual Adaptation On Ctc-based Acoustic Model (2017)0.00