mlsanityData to 14 Oct 2026

Text Injection for Capitalization and Turn-Taking Prediction in Speech Models

arXiv 2308.07395 ↗First posted 14 Aug 2023cs.CL cs.LG cs.SDcited by 1

Not on the map. Why?

Abstract (arXiv)

Text injection for automatic speech recognition (ASR), wherein unpaired text-only data is used to supplement paired audio-text data, has shown promising improvements for word error rate. This study examines the use of text injection for auxiliary tasks, which are the non-ASR tasks often performed by an E2E model. In this work, we use joint end-to-end and internal language model training (JEIT) as our text injection algorithm to train an ASR model which performs two auxiliary tasks. The first is capitalization, which is a de-normalization task. The second is turn-taking prediction, which attempts to identify whether a user has completed their conversation turn in a digital assistant interaction. We show results demonstrating that our text injection method boosts capitalization performance for long-tail data, and improves turn-taking detection recall.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 26 of its 38 references that are in the map. First posted on arXiv 14 Aug 2023.

Builds on

26 of 38 references.

References · 26

  1. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  2. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
  3. 2017An analysis of incorporating an external language model into a sequence-to-sequence modelcited by 111
  4. 2020Hybrid Autoregressive Transducer (hat)cited by 108
  5. 2020A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latencycited by 100
  6. 2020Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognitioncited by 80
  7. 2022MAESTRO: Matched Speech Text Representations through Modality Matchingcited by 79
  8. 2019Recognizing long-form speech using streaming end-to-end modelscited by 77
  9. 2020Cascaded encoders for unifying streaming and non-streaming ASRcited by 53
  10. 2019Joint Speech Recognition and Speaker Diarization via Sequence Transductioncited by 49
  11. 2022JOIST: A Joint Speech and Text Streaming Model For ASRcited by 24
  12. 2022Integrating Text Inputs For Training and Adapting RNN Transducer ASR Modelscited by 20
14 more
  1. 2018Device-directed Utterance Detectioncited by 19
  2. 2021Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognitioncited by 17
  3. 2022E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASRcited by 17
  4. 2022Modular Hybrid Autoregressive Transducercited by 17
  5. 2020Robust Prediction of Punctuation and Truecasing for Medical ASRcited by 16
  6. 2022Turn-Taking Prediction for Natural Conversational Speechcited by 15
  7. 2019Fast and Accurate Capitalization and Punctuation for Automatic Speech Recognition Using Transformer and Chunk Mergingcited by 14
  8. 2023Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generatorcited by 11
  9. 2022Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech Recognitioncited by 10
  10. 2023JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognitioncited by 9
  11. 2017Joint Learning of Correlated Sequence Labelling Tasks Using Bidirectional Recurrent Neural Networkscited by 6
  12. 2022Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systemscited by 5
  13. 2022Capitalization Normalization for Language Modeling with an Accurate and Efficient Hierarchical RNN Modelcited by 3
  14. 2022Streaming Intended Query Detection using E2E Modeling for Continued Conversationcited by 3

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Text Injection for Neural Contextual Biasingcited by 3