Integrating Text Inputs For Training and Adapting RNN Transducer ASR Models

• URL: http://arxiv.org/abs/2202.13155v1
• Date: Sat, 26 Feb 2022 15:03:09 GMT
• Title: Integrating Text Inputs For Training and Adapting RNN Transducer ASR Models
• Authors: Samuel Thomas, Brian Kingsbury, George Saon, Hong-Kwang J. Kuo
• Abstract summary: We propose a novel text representation and training framework for E2E ASR models. We show that a trained RNN Transducer (RNN-T) model's internal LM component can be effectively adapted with text-only data.
• Score: 29.256853083988634
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Compared to hybrid automatic speech recognition (ASR) systems that use a modular architecture in which each component can be independently adapted to a new domain, recent end-to-end (E2E) ASR system are harder to customize due to their all-neural monolithic construction. In this paper, we propose a novel text representation and training framework for E2E ASR models. With this approach, we show that a trained RNN Transducer (RNN-T) model's internal LM component can be effectively adapted with text-only data. An RNN-T model trained using both speech and text inputs improves over a baseline model trained on just speech with close to 13% word error rate (WER) reduction on the Switchboard and CallHome test sets of the NIST Hub5 2000 evaluation. The usefulness of the proposed approach is further demonstrated by customizing this general purpose RNN-T model to three separate datasets. We observe 20-45% relative word error rate (WER) reduction in these settings with this novel LM style customization technique using only unpaired text data from the new domains.

Related papers

• Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator [17.44686265224974]
  We propose an end-to-end Automatic Speech Recognition (ASR) system that can be trained on transcribed speech data, text-only data, or a mixture of both. We demonstrate that the proposed training method significantly improves ASR accuracy compared to the system trained on transcribed speech only.
  arXiv  Detail & Related papers  (2023-02-27T18:47:55Z)
• Multi-blank Transducers for Speech Recognition [49.6154259349501]
  In our proposed method, we introduce additional blank symbols, which consume two or more input frames when emitted. We refer to the added symbols as big blanks, and the method multi-blank RNN-T. With experiments on multiple languages and datasets, we show that multi-blank RNN-T methods could bring relative speedups of over +90%/+139%.
  arXiv  Detail & Related papers  (2022-11-04T16:24:46Z)
• Bayesian Neural Network Language Modeling for Speech Recognition [59.681758762712754]
  State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. In this paper, an overarching full Bayesian learning framework is proposed to account for the underlying uncertainty in LSTM-RNN and Transformer LMs.
  arXiv  Detail & Related papers  (2022-08-28T17:50:19Z)
• Contextual Adapters for Personalized Speech Recognition in Neural Transducers [16.628830937429388]
  We propose training neural contextual adapters for personalization in neural transducer based ASR models. Our approach can not only bias towards user-defined words, but also has the flexibility to work with pretrained ASR models.
  arXiv  Detail & Related papers  (2022-05-26T22:46:28Z)
• A Likelihood Ratio based Domain Adaptation Method for E2E Models [10.510472957585646]
  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.
  arXiv  Detail & Related papers  (2022-01-10T21:22:39Z)
• Neural Model Reprogramming with Similarity Based Mapping for Low-Resource Spoken Command Recognition [71.96870151495536]
  We propose a novel adversarial reprogramming (AR) approach for low-resource spoken command recognition (SCR) The AR procedure aims to modify the acoustic signals (from the target domain) to repurpose a pretrained SCR model. We evaluate the proposed AR-SCR system on three low-resource SCR datasets, including Arabic, Lithuanian, and dysarthric Mandarin speech.
  arXiv  Detail & Related papers  (2021-10-08T05:07:35Z)
• The USYD-JD Speech Translation System for IWSLT 2021 [85.64797317290349]
  This paper describes the University of Sydney& JD's joint submission of the IWSLT 2021 low resource speech translation task. We trained our models with the officially provided ASR and MT datasets. To achieve better translation performance, we explored the most recent effective strategies, including back translation, knowledge distillation, multi-feature reranking and transductive finetuning.
  arXiv  Detail & Related papers  (2021-07-24T09:53:34Z)
• 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)
• A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings [50.524054820564395]
  We propose a new unsupervised model for mapping a variable-duration speech segment to a fixed-dimensional representation. The resulting acoustic word embeddings can form the basis of search, discovery, and indexing systems for low- and zero-resource languages.
  arXiv  Detail & Related papers  (2020-12-03T19:24:42Z)
• 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)
• Joint Contextual Modeling for ASR Correction and Language Understanding [60.230013453699975]
  We propose multi-task neural approaches to perform contextual language correction on ASR outputs jointly with language understanding (LU) We show that the error rates of off the shelf ASR and following LU systems can be reduced significantly by 14% relative with joint models trained using small amounts of in-domain data.
  arXiv  Detail & Related papers  (2020-01-28T22:09:25Z)

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.