mlsanityData to 14 Oct 2026

ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMs

arXiv 2305.10649 ↗First posted 18 May 2023cs.SD cs.CL eess.AScited by 13

Not on the map. Why?

Abstract (arXiv)

In this paper, we present ZeroPrompt (Figure 1-(a)) and the corresponding Prompt-and-Refine strategy (Figure 3), two simple but effective training-free methods to decrease the Token Display Time (TDT) of streaming ASR models without any accuracy loss. The core idea of ZeroPrompt is to append zeroed content to each chunk during inference, which acts like a prompt to encourage the model to predict future tokens even before they were spoken. We argue that streaming acoustic encoders naturally have the modeling ability of Masked Language Models and our experiments demonstrate that ZeroPrompt is engineering cheap and can be applied to streaming acoustic encoders on any dataset without any accuracy loss. Specifically, compared with our baseline models, we achieve 350 ~ 700ms reduction on First Token Display Time (TDT-F) and 100 ~ 400ms reduction on Last Token Display Time (TDT-L), with theoretically and experimentally equal WER on both Aishell-1 and Librispeech datasets.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 15 of its 24 references that are in the map. First posted on arXiv 18 May 2023.

Builds on

15 of 24 references.

References · 15

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 373
  4. 2019Generative Pre-Training for Speech with Autoregressive Predictive Codingcited by 82
  5. 2020FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularizationcited by 69
  6. 2022WeNet 2.0: More Productive End-to-End Speech Recognition Toolkitcited by 47
  7. 2020Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognitioncited by 39
  8. 2020Streaming Transformer-based Acoustic Models Using Self-attention with Augmented Memorycited by 35
  9. 2019Self-Attention Aligner: A Latency-Control End-to-End Model for ASR Using Self-Attention Network and Chunk-Hoppingcited by 33
  10. 2021Dissecting User-Perceived Latency of On-Device E2E Speech Recognitioncited by 19
  11. 2022CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASRcited by 11
  12. 2023Adaptable End-to-End ASR Models using Replaceable Internal LMs and Residual Softmaxcited by 8
3 more
  1. 2022TrimTail: Low-Latency Streaming ASR with Simple but Effective Spectrogram-Level Length Penaltycited by 6
  2. 2022Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First Regularizationcited by 6
  3. 2022Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategiescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 12; 2025: 0; 2026: 1.

13 papers.

Sort:

By area:

  1. 2024Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Reviewcited by 53
  2. 2024Exploring Diverse Methods in Visual Question Answeringcited by 45
  3. 2024Accelerating Parallel Sampling of Diffusion Modelscited by 30
  4. 2024Harnessing Earnings Reports for Stock Predictions: A QLoRA-Enhanced LLM Approachcited by 24
  5. 2024Ensemble Methodology:Innovations in Credit Default Prediction Using LightGBM, XGBoost, and LocalEnsemblecited by 8
  6. 2024Integration of Mamba and Transformer -- MAT for Long-Short Range Time Series Forecasting with Application to Weather Dynamicscited by 7
  7. 2024Research on Credit Risk Early Warning Model of Commercial Banks Based on Neural Network Algorithmcited by 5
  8. 2024Leveraging Contrastive Learning and Self-Training for Multimodal Emotion Recognition with Limited Labeled Samplescited by 5
  9. 2024Optimization and Application of Cloud-based Deep Learning Architecture for Multi-Source Data Predictioncited by 5
  10. 2024MEDFuse: Multimodal EHR Data Fusion with Masked Lab-Test Modeling and Large Language Modelscited by 3
  11. 2024Enhancing Exchange Rate Forecasting with Explainable Deep Learning Modelscited by 2
  12. 2024Wormhole: Concept-Aware Deep Representation Learning for Co-Evolving Sequencescited by 1
1 more
  1. 2026SENS-ASR: Semantic Embedding injection in Neural-transducer for Streaming Automatic Speech Recognitioncited by 0