Initial Decoding with Minimally Augmented Language Model for Improved Lattice Rescoring in Low Resource ASR

• URL: http://arxiv.org/abs/2403.10937v1
• Date: Sat, 16 Mar 2024 14:34:31 GMT
• Title: Initial Decoding with Minimally Augmented Language Model for Improved Lattice Rescoring in Low Resource ASR
• Authors: Savitha Murthy, Dinkar Sitaram,
• Abstract summary: This paper addresses the problem of improving speech recognition accuracy with lattice rescoring in low-resource languages. We minimally augment the baseline language model with word unigram counts that are present in a larger text corpus of the target language but absent in the baseline. We obtain 21.8% (Telugu) and 41.8% (Kannada) relative word error reduction with our proposed method.
• Score: 0.532018200832244
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper addresses the problem of improving speech recognition accuracy with lattice rescoring in low-resource languages where the baseline language model is insufficient for generating inclusive lattices. We minimally augment the baseline language model with word unigram counts that are present in a larger text corpus of the target language but absent in the baseline. The lattices generated after decoding with such an augmented baseline language model are more comprehensive. We obtain 21.8% (Telugu) and 41.8% (Kannada) relative word error reduction with our proposed method. This reduction in word error rate is comparable to 21.5% (Telugu) and 45.9% (Kannada) relative word error reduction obtained by decoding with full Wikipedia text augmented language mode while our approach consumes only 1/8th the memory. We demonstrate that our method is comparable with various text selection-based language model augmentation and also consistent for data sets of different sizes. Our approach is applicable for training speech recognition systems under low resource conditions where speech data and compute resources are insufficient, while there is a large text corpus that is available in the target language. Our research involves addressing the issue of out-of-vocabulary words of the baseline in general and does not focus on resolving the absence of named entities. Our proposed method is simple and yet computationally less expensive.

Related papers

• Language Models for Text Classification: Is In-Context Learning Enough? [54.869097980761595]
  Recent foundational language models have shown state-of-the-art performance in many NLP tasks in zero- and few-shot settings. An advantage of these models over more standard approaches is the ability to understand instructions written in natural language (prompts) This makes them suitable for addressing text classification problems for domains with limited amounts of annotated instances.
  arXiv  Detail & Related papers  (2024-03-26T12:47:39Z)
• LIMIT: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages [27.675441924635294]
  Current systems cannot accurately identify most of the world's 7000 languages. We first compile a corpus, MCS-350, of 50K multilingual and parallel children's stories in 350+ languages. We propose a novel misprediction-resolution hierarchical model, LIMIt, for language identification.
  arXiv  Detail & Related papers  (2023-05-23T17:15:43Z)
• DPCSpell: A Transformer-based Detector-Purificator-Corrector Framework for Spelling Error Correction of Bangla and Resource Scarce Indic Languages [1.7205106391379026]
  Spelling error correction is the task of identifying and rectifying misspelled words in texts. Earlier efforts on spelling error correction in Bangla and resource-scarce Indic languages focused on rule-based, statistical, and machine learning-based methods. We propose a novel detector-purificator-corrector framework based on denoising transformers by addressing previous issues.
  arXiv  Detail & Related papers  (2022-11-07T17:59:05Z)
• No Language Left Behind: Scaling Human-Centered Machine Translation [69.28110770760506]
  We create datasets and models aimed at narrowing the performance gap between low and high-resource languages. We propose multiple architectural and training improvements to counteract overfitting while training on thousands of tasks. Our model achieves an improvement of 44% BLEU relative to the previous state-of-the-art.
  arXiv  Detail & Related papers  (2022-07-11T07:33:36Z)
• Lexically Aware Semi-Supervised Learning for OCR Post-Correction [90.54336622024299]
  Much of the existing linguistic data in many languages of the world is locked away in non-digitized books and documents. Previous work has demonstrated the utility of neural post-correction methods on recognition of less-well-resourced languages. We present a semi-supervised learning method that makes it possible to utilize raw images to improve performance.
  arXiv  Detail & Related papers  (2021-11-04T04:39:02Z)
• Transfer Learning based Speech Affect Recognition in Urdu [0.0]
  We pre-train a model for high resource language affect recognition task and fine tune the parameters for low resource language. This approach achieves high Unweighted Average Recall (UAR) when compared with existing algorithms.
  arXiv  Detail & Related papers  (2021-03-05T10:30:58Z)
• Comparison of Interactive Knowledge Base Spelling Correction Models for Low-Resource Languages [81.90356787324481]
  Spelling normalization for low resource languages is a challenging task because the patterns are hard to predict. This work shows a comparison of a neural model and character language models with varying amounts on target language data. Our usage scenario is interactive correction with nearly zero amounts of training examples, improving models as more data is collected.
  arXiv  Detail & Related papers  (2020-10-20T17:31:07Z)
• Deep Learning Models for Multilingual Hate Speech Detection [5.977278650516324]
  In this paper, we conduct a large scale analysis of multilingual hate speech in 9 languages from 16 different sources. We observe that in low resource setting, simple models such as LASER embedding with logistic regression performs the best. In case of zero-shot classification, languages such as Italian and Portuguese achieve good results.
  arXiv  Detail & Related papers  (2020-04-14T13:14:27Z)
• Towards Zero-shot Learning for Automatic Phonemic Transcription [82.9910512414173]
  A more challenging problem is to build phonemic transcribers for languages with zero training data. Our model is able to recognize unseen phonemes in the target language without any training data. It achieves 7.7% better phoneme error rate on average over a standard multilingual model.
  arXiv  Detail & Related papers  (2020-02-26T20:38:42Z)
• Rnn-transducer with language bias for end-to-end Mandarin-English code-switching speech recognition [58.105818353866354]
  We propose an improved recurrent neural network transducer (RNN-T) model with language bias to alleviate the problem. We use the language identities to bias the model to predict the CS points. This promotes the model to learn the language identity information directly from transcription, and no additional LID model is needed.
  arXiv  Detail & Related papers  (2020-02-19T12:01:33Z)

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.