Streaming Sequence Transduction through Dynamic Compression
Not on the map. Why?
Abstract (arXiv)
We introduce STAR (Stream Transduction with Anchor Representations), a novel Transformer-based model designed for efficient sequence-to-sequence transduction over streams. STAR dynamically segments input streams to create compressed anchor representations, achieving nearly lossless compression (12x) in Automatic Speech Recognition (ASR) and outperforming existing methods. Moreover, STAR demonstrates superior segmentation and latency-quality trade-offs in simultaneous speech-to-text tasks, optimizing latency, memory footprint, and quality.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 43 of its 70 references that are in the map. First posted on arXiv 2 Feb 2024.
Builds on
43 of 70 references.
References · 43
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
- 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
- 2020Longformer: The Long-Document Transformercited by 3,362
- 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
- 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
- 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
- 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
- 2023Efficient Streaming Language Models with Attention Sinkscited by 2,115
- 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
31 more
- 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
- 2020Rethinking Attention with Performerscited by 1,584
- 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
- 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
- 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
- 2020Efficient Transformers: A Surveycited by 784
- 2021SoundStream: An End-to-End Neural Audio Codeccited by 756
- 2019Compressive Transformers for Long-Range Sequence Modellingcited by 699
- 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 639
- 2021W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Trainingcited by 340
- 2015A Critical Review of Recurrent Neural Networks for Sequence Learningcited by 223
- 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
- 2023Focused Transformer: Contrastive Training for Context Scalingcited by 133
- 2023End-to-End Speech Recognition: A Surveycited by 127
- 2023Unlimiformer: Long-Range Transformers with Unlimited Length Inputcited by 127
- 2019Monotonic Infinite Lookback Attention for Simultaneous Machine Translationcited by 103
- 2020SimulEval: An Evaluation Toolkit for Simultaneous Translationcited by 94
- 2019Monotonic Multihead Attentioncited by 91
- 2020SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translationcited by 80
- 2019CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognitioncited by 76
- 2020Streaming automatic speech recognition with the transformer modelcited by 73
- 2019End-to-End Speech Translation with Knowledge Distillationcited by 58
- 2021RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformercited by 39
- 2021Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASRcited by 31
- 2022Large-Scale Streaming End-to-End Speech Translation with Neural Transducerscited by 31
- 2021Learning When to Translate for Streaming Speechcited by 30
- 2020Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASRcited by 19
- 2023Nugget: Neural Agglomerative Embeddings of Textcited by 19
- 2022Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translationcited by 14
- 2022LAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducerscited by 10
- 2021FastS2S-VC: Streaming Non-Autoregressive Sequence-to-Sequence Voice Conversioncited by 5
Built on by
Citing papers per year: 2024: 2.
2 papers.