Effective internal language model training and fusion for factorized transducer model

• URL: http://arxiv.org/abs/2404.01716v1
• Date: Tue, 2 Apr 2024 08:01:05 GMT
• Title: Effective internal language model training and fusion for factorized transducer model
• Authors: Jinxi Guo, Niko Moritz, Yingyi Ma, Frank Seide, Chunyang Wu, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer,
• Abstract summary: Internal language model (ILM) of the neural transducer has been widely studied. We propose a novel ILM training and decoding strategy for factorized transducer models.
• Score: 26.371223360905557
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The internal language model (ILM) of the neural transducer has been widely studied. In most prior work, it is mainly used for estimating the ILM score and is subsequently subtracted during inference to facilitate improved integration with external language models. Recently, various of factorized transducer models have been proposed, which explicitly embrace a standalone internal language model for non-blank token prediction. However, even with the adoption of factorized transducer models, limited improvement has been observed compared to shallow fusion. In this paper, we propose a novel ILM training and decoding strategy for factorized transducer models, which effectively combines the blank, acoustic and ILM scores. Our experiments show a 17% relative improvement over the standard decoding method when utilizing a well-trained ILM and the proposed decoding strategy on LibriSpeech datasets. Furthermore, when compared to a strong RNN-T baseline enhanced with external LM fusion, the proposed model yields a 5.5% relative improvement on general-sets and an 8.9% WER reduction for rare words. The proposed model can achieve superior performance without relying on external language models, rendering it highly efficient for production use-cases. To further improve the performance, we propose a novel and memory-efficient ILM-fusion-aware minimum word error rate (MWER) training method which improves ILM integration significantly.

Related papers

• FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models [50.331708897857574]
  We introduce FactorLLM, a novel approach that decomposes well-trained dense FFNs into sparse sub-networks without requiring any further modifications. FactorLLM achieves comparable performance to the source model securing up to 85% model performance while obtaining over a 30% increase in inference speed.
  arXiv  Detail & Related papers  (2024-08-15T16:45:16Z)
• Unlocking the Potential of Model Merging for Low-Resource Languages [66.7716891808697]
  Adapting large language models to new languages typically involves continual pre-training (CT) followed by supervised fine-tuning (SFT) We propose model merging as an alternative for low-resource languages, combining models with distinct capabilities into a single model without additional training. Experiments based on Llama-2-7B demonstrate that model merging effectively endows LLMs for low-resource languages with task-solving abilities, outperforming CT-then-SFT in scenarios with extremely scarce data.
  arXiv  Detail & Related papers  (2024-07-04T15:14:17Z)
• ALMol: Aligned Language-Molecule Translation LLMs through Offline Preference Contrastive Optimisation [2.296475290901356]
  We focus on machine language-molecule translation and deploy a novel training approach called contrastive preference optimisation. Our results demonstrate that our models achieve up to a 32% improvement compared to counterpart models.
  arXiv  Detail & Related papers  (2024-05-14T13:59:24Z)
• External Language Model Integration for Factorized Neural Transducers [7.5969913968845155]
  We propose an adaptation method for factorized neural transducers (FNT) with external language models. We show average gains of 18% WERR with lexical adaptation across various scenarios and additive gains of up to 60% WERR in one entity-rich scenario.
  arXiv  Detail & Related papers  (2023-05-26T23:30:21Z)
• EMS: Efficient and Effective Massively Multilingual Sentence Embedding Learning [38.928786416891924]
  We introduce efficient and effective massively multilingual sentence embedding (EMS) using cross-lingual token-level reconstruction (XTR) and sentence-level contrastive learning as training objectives. Compared with related studies, the proposed model can be efficiently trained using significantly fewer parallel sentences and GPU computation resources. We release the codes for model training and the EMS pre-trained sentence embedding model, which supports 62 languages.
  arXiv  Detail & Related papers  (2022-05-31T12:29:25Z)
• Improving Rare Word Recognition with LM-aware MWER Training [50.241159623691885]
  We introduce LMs in the learning of hybrid autoregressive transducer (HAT) models in the discriminative training framework. For the shallow fusion setup, we use LMs during both hypotheses generation and loss computation, and the LM-aware MWER-trained model achieves 10% relative improvement. For the rescoring setup, we learn a small neural module to generate per-token fusion weights in a data-dependent manner.
  arXiv  Detail & Related papers  (2022-04-15T17:19:41Z)
• Factorized Neural Transducer for Efficient Language Model Adaptation [51.81097243306204]
  We propose a novel model, factorized neural Transducer, by factorizing the blank and vocabulary prediction. It is expected that this factorization can transfer the improvement of the standalone language model to the Transducer for speech recognition. We demonstrate that the proposed factorized neural Transducer yields 15% to 20% WER improvements when out-of-domain text data is used for language model adaptation.
  arXiv  Detail & Related papers  (2021-09-27T15:04:00Z)
• Distributionally Robust Multilingual Machine Translation [94.51866646879337]
  We propose a new learning objective for Multilingual neural machine translation (MNMT) based on distributionally robust optimization. We show how to practically optimize this objective for large translation corpora using an iterated best response scheme. Our method consistently outperforms strong baseline methods in terms of average and per-language performance under both many-to-one and one-to-many translation settings.
  arXiv  Detail & Related papers  (2021-09-09T03:48:35Z)
• Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models [107.86965028729517]
  Attention-based encoder-decoder (AED) models learn an implicit internal language model (ILM) from the training transcriptions. We propose several novel methods to estimate the ILM directly from the AED model.
  arXiv  Detail & Related papers  (2021-04-12T15:16:03Z)
• Early Stage LM Integration Using Local and Global Log-Linear Combination [46.91755970827846]
  Sequence-to-sequence models with an implicit alignment mechanism (e.g. attention) are closing the performance gap towards traditional hybrid hidden Markov models (HMM) One important factor to improve word error rate in both cases is the use of an external language model (LM) trained on large text-only corpora. We present a novel method for language model integration into implicit-alignment based sequence-to-sequence models.
  arXiv  Detail & Related papers  (2020-05-20T13:49:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.