paper-with-me

홈 › Papers

Continual Learning Optimizations for Auto-regressive Decoder of Multilingual ASR systems

2024-07-04 · Chin Yuen Kwok, Jia Qi Yip, Eng Siong Chng

Continual Learning (CL) involves fine-tuning pre-trained models with new data while maintaining the performance on the pre-trained data. This is particularly relevant for expanding multilingual ASR (MASR) capabilities. However, existing CL methods, mainly designed for computer vision and reinforcement learning tasks, often yield sub-optimal results when directly applied to MASR. We hypothesise that this is because CL of the auto-regressive decoder in the MASR model is difficult. To verify this, we propose four optimizations on the decoder. They include decoder-layer gradient surgery, freezing unused token embeddings, suppressing output of newly added tokens, and learning rate re-scaling. Our experiments on adapting Whisper to 10 unseen languages from the Common Voice dataset demonstrate that these optimizations reduce the Average Word Error Rate (AWER) of pretrained languages from 14.2% to 12.4% compared with Experience Replay, without compromising the AWER of new languages.

📄 PDF Abstract BibTeX arXiv:2407.03645

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningDecoder

Methods 이 논문이 사용한 방법론

Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…

Similar Papers 제목 키워드 기반

Non-Autoregressive Models are Better Multilingual Translators

2021-09-29 · ICLR 2022 4 · Zhenqiao Song, Hao Zhou, Lihua Qian, Jingjing Xu 외

Multilingual machine translation aims to develop a single model for multiple language directions. However, existing multilingual models based on Transformer are limited in terms of both translation performance and infere…

DecoderMachine TranslationSentenceTranslation

On the Analysis of Cross-Lingual Prompt Tuning for Decoder-based Multilingual Model

2023-11-14 · Nohil Park, Joonsuk Park, Kang Min Yoo, Sungroh Yoon

An exciting advancement in the field of multilingual models is the emergence of autoregressive models with zero- and few-shot capabilities, a phenomenon widely reported in large-scale language models. To further improve …

DecoderNERparameter-efficient fine-tuningPOS

Whisfusion: Parallel ASR Decoding with Masked Diffusion

2025-08-09 · Taeyoun Kwon, Junhyuk Ahn, Taegeun Yun, Heeju Jwa 외 arxiv

Autoregressive (AR) encoder-decoder models dominate high-quality multilingual ASR, but their left-to-right decoders make inference latency scale with transcript length. A natural alternative, CTC-style non-autoregressive…

OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification

2024-02-20 · Yifan Peng, Yui Sudo, Muhammad Shakeel, Shinji Watanabe

There has been an increasing interest in large speech models that can perform multiple tasks in a single model. Such models usually adopt an encoder-decoder or decoder-only architecture due to their popularity and good p…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderHallucination+5

Variational Auto-Regressive Gaussian Processes for Continual Learning

2020-06-09 · Sanyam Kapoor, Theofanis Karaletsos, Thang D. Bui

Through sequential construction of posteriors on observing data online, Bayes' theorem provides a natural framework for continual learning. We develop Variational Auto-Regressive Gaussian Processes (VAR-GPs), a principle…

Bayesian InferenceContinual LearningGaussian Processes