mlsanityData to 14 Oct 2026

SENS-ASR: Semantic Embedding injection in Neural-transducer for Streaming Automatic Speech Recognition

arXiv 2603.10005 ↗First posted 17 Feb 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Many Automatic Speech Recognition (ASR) applications require streaming processing of the audio data. In streaming mode, ASR systems need to start transcribing the input stream before it is complete, i.e., the systems have to process a stream of inputs with a limited (or no) future context. Compared to offline mode, this reduction of the future context degrades the performance of Streaming-ASR systems, especially while working with low-latency constraint. In this work, we present SENS-ASR, an approach to enhance the transcription quality of Streaming-ASR by reinforcing the acoustic information with semantic information. This semantic information is extracted from the available past frame-embeddings by a context module. This module is trained using knowledge distillation from a sentence embedding Language Model fine-tuned on the training dataset transcriptions. Experiments on standard datasets show that SENS-ASR significantly improves the Word Error Rate on small-chunk streaming scenarios.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 53 references that are in the map. First posted on arXiv 17 Feb 2026.

Builds on

29 of 53 references.

References · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  5. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  6. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 981
  7. 2020Prevalence of Neural Collapse during the terminal phase of deep learning trainingcited by 719
  8. 2015Listen, Attend and Spellcited by 543
  9. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 406
  10. 2019NeMo: a toolkit for building AI applications using Neural Modulescited by 235
  11. 2024Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMscited by 229
  12. 2023SONAR: Sentence-Level Multimodal and Language-Agnostic Representationscited by 108
17 more
  1. 2023SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translationcited by 76
  2. 2020FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularizationcited by 69
  3. 2020Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognitioncited by 39
  4. 2020Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducercited by 22
  5. 2020The RWTH ASR System for TED-LIUM Release 2: Improving Hybrid HMM with SpecAugmentcited by 19
  6. 2021Dual Causal/Non-Causal Self-Attention for Streaming End-to-End Speech Recognitioncited by 14
  7. 2023ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMscited by 13
  8. 2024Do We Need Domain-Specific Embedding Models? An Empirical Investigationcited by 12
  9. 2022CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASRcited by 11
  10. 2022Global Normalization for Streaming Speech Recognition in a Modular Frameworkcited by 10
  11. 2018Enhancing Sentence Embedding with Generalized Poolingcited by 8
  12. 2022Delay-penalized transducer for low-latency streaming ASRcited by 7
  13. 2023Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognitioncited by 7
  14. 2022TrimTail: Low-Latency Streaming ASR with Simple but Effective Spectrogram-Level Length Penaltycited by 6
  15. 2023Delay-penalized CTC implemented based on Finite State Transducercited by 4
  16. 2024CUSIDE-T: Chunking, Simulating Future and Decoding for Transducer based Streaming ASRcited by 3
  17. 2022SSCFormer: Push the Limit of Chunk-wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolutioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper
  2. 2024Joint Optimization of Streaming and Non-Streaming Automatic Speech Recognition with Multi-Decoder and Knowledge Distillation
  3. 2023Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer
  4. 2022Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategies
  5. 2021Knowledge Distillation for Neural Transducers from Large Self-Supervised Pre-trained Models
  6. 2022Contextual-Utterance Training for Automatic Speech Recognition
  7. 2023Reducing the gap between streaming and non-streaming Transducer-based ASR by adaptive two-stage knowledge distillation
  8. 2021Bridging the gap between streaming and non-streaming ASR systems bydistilling ensembles of CTC and RNN-T models