paper-with-me

홈 › Papers

Enhancing Multilingual ASR for Unseen Languages via Language Embedding Modeling

2024-12-21 · Shao-Syuan Huang, Kuan-Po Huang, Andy T. Liu, Hung-Yi Lee

Multilingual Automatic Speech Recognition (ASR) aims to recognize and transcribe speech from multiple languages within a single system. Whisper, one of the most advanced ASR models, excels in this domain by handling 99 languages effectively, leveraging a vast amount of data and incorporating language tags as prefixes to guide the recognition process. However, despite its success, Whisper struggles with unseen languages, those not included in its pre-training. Motivated by the observation that many languages share linguistic characteristics, we propose methods that exploit these relationships to enhance ASR performance on unseen languages. Specifically, we introduce a weighted sum method, which computes a weighted sum of the embeddings of language tags, using Whisper's predicted language probabilities. In addition, we develop a predictor-based approach that refines the weighted sum embedding to more closely approximate the true embedding for unseen languages. Experimental results demonstrate substantial improvements in ASR performance, both in zero-shot and fine-tuning settings. Our proposed methods outperform baseline approaches, providing an effective solution for addressing unseen languages in multilingual ASR.

📄 PDF Abstract BibTeX arXiv:2412.16474

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Enhancing Multilingual Embeddings via Multi-Way Parallel Text Alignment

2026-02-25 · Barah Fazili, Koustava Goswami arxiv

Multilingual pretraining typically lacks explicit alignment signals, leading to suboptimal cross-lingual alignment in the representation space. In this work, we show that training standard pretrained models for cross-lin…

Contrastive LearningSemantic Similarity

UNKs Everywhere: Adapting Multilingual Language Models to New Scripts

2020-12-31 · EMNLP 2021 11 · Jonas Pfeiffer, Ivan Vulić, Iryna Gurevych, Sebastian Ruder

Massively multilingual language models such as multilingual BERT offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks. However, due to limited capacity and large differences in pretraining da…

Cross-Lingual Transfer

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

2022-11-10 · Andros Tjandra, Nayan Singhal, David Zhang, Ozlem Kalinli 외

End-to-end multilingual ASR has become more appealing because of several reasons such as simplifying the training and deployment process and positive performance transfer from high-resource to low-resource languages. How…

Improved acoustic word embeddings for zero-resource languages using multilingual transfer

2020-06-02 · Herman Kamper, Yevgen Matusevych, Sharon Goldwater

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. Such embeddings can form the basis for speech search, indexing and discovery systems when conventional speech recognition…

speech-recognitionSpeech RecognitionWord Embeddings

Cross-lingual Word Embeddings beyond Zero-shot Machine Translation

2020-11-03 · Shifei Chen, Ali Basirat

We explore the transferability of a multilingual neural machine translation model to unseen languages when the transfer is grounded solely on the cross-lingual word embeddings. Our experimental results show that the tran…

Cross-Lingual Word EmbeddingsMachine TranslationTranslationWord Embeddings+1