A Likelihood Ratio based Domain Adaptation Method for E2E Models

• URL: http://arxiv.org/abs/2201.03655v1
• Date: Mon, 10 Jan 2022 21:22:39 GMT
• Title: A Likelihood Ratio based Domain Adaptation Method for E2E Models
• Authors: Chhavi Choudhury, Ankur Gandhe, Xiaohan Ding, Ivan Bulyko
• Abstract summary: End-to-end (E2E) automatic speech recognition models like Recurrent Neural Networks Transducer (RNN-T) are becoming a popular choice for streaming ASR applications like voice assistants. While E2E models are very effective at learning representation of the training data they are trained on, their accuracy on unseen domains remains a challenging problem. In this work, we explore a contextual biasing approach using likelihood-ratio that leverages text data sources to adapt RNN-T model to new domains and entities.
• Score: 10.510472957585646
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: End-to-end (E2E) automatic speech recognition models like Recurrent Neural Networks Transducer (RNN-T) are becoming a popular choice for streaming ASR applications like voice assistants. While E2E models are very effective at learning representation of the training data they are trained on, their accuracy on unseen domains remains a challenging problem. Additionally, these models require paired audio and text training data, are computationally expensive and are difficult to adapt towards the fast evolving nature of conversational speech. In this work, we explore a contextual biasing approach using likelihood-ratio that leverages text data sources to adapt RNN-T model to new domains and entities. We show that this method is effective in improving rare words recognition, and results in a relative improvement of 10% in 1-best word error rate (WER) and 10% in n-best Oracle WER (n=8) on multiple out-of-domain datasets without any degradation on a general dataset. We also show that complementing the contextual biasing adaptation with adaptation of a second-pass rescoring model gives additive WER improvements.

Related papers

• Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation [73.9145653659403]
  We show that Generative Error Correction models struggle to generalize beyond the specific types of errors encountered during training. We propose DARAG, a novel approach designed to improve GEC for ASR in in-domain (ID) and OOD scenarios. Our approach is simple, scalable, and both domain- and language-agnostic.
  arXiv  Detail & Related papers  (2024-10-17T04:00:29Z)
• Decoupled Structure for Improved Adaptability of End-to-End Models [16.195423291103975]
  This paper proposes decoupled structures for attention-based encoder-decoder (Decoupled-AED) and neural transducer (Decoupled-Transducer) models. The acoustic and linguistic parts of the E2E model decoder (or prediction network) are decoupled, making the linguistic component replaceable. Experiments for E2E ASR models trained on the Libri-100h corpus showed that the proposed decoupled structure gave 15.1% and 17.2% relative word error rate reductions.
  arXiv  Detail & Related papers  (2023-08-25T12:31:12Z)
• Using External Off-Policy Speech-To-Text Mappings in Contextual End-To-End Automated Speech Recognition [19.489794740679024]
  We investigate the potential of leveraging external knowledge, particularly through off-policy key-value stores generated with text-to-speech methods. In our approach, audio embeddings captured from text-to-speech, along with semantic text embeddings, are used to bias ASR. Experiments on LibiriSpeech and in-house voice assistant/search datasets show that the proposed approach can reduce domain adaptation time by up to 1K GPU-hours.
  arXiv  Detail & Related papers  (2023-01-06T22:32:50Z)
• 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)
• On Addressing Practical Challenges for RNN-Transduce [72.72132048437751]
  We adapt a well-trained RNN-T model to a new domain without collecting the audio data. We obtain word-level confidence scores by utilizing several types of features calculated during decoding. The proposed time stamping method can get less than 50ms word timing difference on average.
  arXiv  Detail & Related papers  (2021-04-27T23:31:43Z)
• Fast Text-Only Domain Adaptation of RNN-Transducer Prediction Network [0.0]
  We show that RNN-transducer models can be effectively adapted to new domains using only small amounts of textual data. We show with multiple ASR evaluation tasks how this method can provide relative gains of 10-45% in target task WER.
  arXiv  Detail & Related papers  (2021-04-22T15:21:41Z)
• Pretraining Techniques for Sequence-to-Sequence Voice Conversion [57.65753150356411]
  Sequence-to-sequence (seq2seq) voice conversion (VC) models are attractive owing to their ability to convert prosody. We propose to transfer knowledge from other speech processing tasks where large-scale corpora are easily available, typically text-to-speech (TTS) and automatic speech recognition (ASR) We argue that VC models with such pretrained ASR or TTS model parameters can generate effective hidden representations for high-fidelity, highly intelligible converted speech.
  arXiv  Detail & Related papers  (2020-08-07T11:02:07Z)
• Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability [46.73349163361723]
  Recurrent neural network transducer (RNN-T) is a promising end-to-end (E2E) model that may replace the popular hybrid model for automatic speech recognition. We describe our recent development of RNN-T models with reduced GPU memory consumption during training. We study how to customize RNN-T models to a new domain, which is important for deploying E2E models to practical scenarios.
  arXiv  Detail & Related papers  (2020-07-30T02:35:20Z)
• Contextual RNN-T For Open Domain ASR [41.83409885125617]
  End-to-end (E2E) systems for automatic speech recognition (ASR) blend the individual components of a traditional hybrid ASR system into a single neural network. This has some nice advantages, it limits the system to be trained using only paired audio and text. Because of this, E2E models tend to have difficulties with correctly recognizing rare words that are not frequently seen during training, such as entity names. We propose modifications to the RNN-T model that allow the model to utilize additional metadata text with the objective of improving performance on these named entity words.
  arXiv  Detail & Related papers  (2020-06-04T04:37:03Z)
• Hybrid Generative-Retrieval Transformers for Dialogue Domain Adaptation [77.62366712130196]
  We present the winning entry at the fast domain adaptation task of DSTC8, a hybrid generative-retrieval model based on GPT-2 fine-tuned to the multi-domain MetaLWOz dataset. Our model uses retrieval logic as a fallback, being SoTA on MetaLWOz in human evaluation (>4% improvement over the 2nd place system) and attaining competitive generalization performance in adaptation to the unseen MultiWOZ dataset.
  arXiv  Detail & Related papers  (2020-03-03T18:07:42Z)

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.