Model-free Speculative Decoding for Transformer-based ASR with Token Map Drafting

• URL: http://arxiv.org/abs/2507.21522v1
• Date: Tue, 29 Jul 2025 06:20:04 GMT
• Title: Model-free Speculative Decoding for Transformer-based ASR with Token Map Drafting
• Authors: Tuan Vu Ho, Hiroaki Kokubo, Masaaki Yamamoto, Yohei Kawaguchi,
• Abstract summary: We propose emphToken Map Drafting, a model-free SD technique that eliminates the need for a separate draft model.<n>Our method significantly accelerates inference ASR in structured, low-perplexity domains without sacrificing transcription accuracy.
• Score: 5.976028696804381
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: End-to-end automatic speech recognition (ASR) systems based on transformer architectures, such as Whisper, offer high transcription accuracy and robustness. However, their autoregressive decoding is computationally expensive, hence limiting deployment on CPU-based and resource-constrained devices. Speculative decoding (SD) mitigates this issue by using a smaller draft model to propose candidate tokens, which are then verified by the main model. However, this approach is impractical for devices lacking hardware accelerators like GPUs. To address this, we propose \emph{Token Map Drafting}, a model-free SD technique that eliminates the need for a separate draft model. Instead, we leverage a precomputed n-gram token map derived from domain-specific training data, enabling efficient speculative decoding with minimal overhead. Our method significantly accelerates ASR inference in structured, low-perplexity domains without sacrificing transcription accuracy. Experimental results demonstrate decoding speed-ups of $1.27\times$ on the CI-AVSR dataset and $1.37\times$ on our internal dataset without degrading recognition accuracy. Additionally, our approach achieves a $10\%$ absolute improvement in decoding speed over the Distill-spec baseline running on CPU, highlighting its effectiveness for on-device ASR applications.

Related papers

• SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving [7.91607650966469]
  acronym is a framework that allows lightweight edge devices to draft multiple candidate tokens locally using diverse draft models.<n>A single, shared edge server verifies the tokens utilizing a more precise target model.<n>Our initial experiments with Jetson Orin Nano, Raspberry Pi 4B/5, and an edge server equipped with 4 Nvidia A100 GPUs indicate substantial benefits.
  arXiv  Detail & Related papers  (2025-06-11T04:55:54Z)
• LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation [23.51191930926061]
  We introduce LiteASR, a low-rank compression scheme for ASR encoders that significantly reduces inference costs while maintaining transcription accuracy.<n> Evaluation results show that our method can compress Whisper large-v3's encoder size by over 50%, matching Whisper medium's size with better transcription accuracy.
  arXiv  Detail & Related papers  (2025-02-27T22:52:21Z)
• SpecHub: Provable Acceleration to Multi-Draft Speculative Decoding [28.76164449548306]
  Multi-Draft Speculative Decoding (MDSD) offers a promising solution by using a smaller draft model to generate multiple token sequences. We present SpecHub, a novel, efficient sampling-verification method for MDSD that improves acceptance rates with only linear computational overhead.
  arXiv  Detail & Related papers  (2024-11-08T02:47:07Z)
• Accurate, Low-latency, Efficient SAR Automatic Target Recognition on FPGA [3.251765107970636]
  Synthetic aperture radar (SAR) automatic target recognition (ATR) is the key technique for remote-sensing image recognition. The state-of-the-art convolutional neural networks (CNNs) for SAR ATR suffer from emphhigh computation cost and emphlarge memory footprint. We propose a comprehensive GNN-based model-architecture co-design on FPGA to address the above issues.
  arXiv  Detail & Related papers  (2023-01-04T05:35:30Z)
• Decoder Tuning: Efficient Language Understanding as Decoding [84.68266271483022]
  We present Decoder Tuning (DecT), which in contrast optimize task-specific decoder networks on the output side. By gradient-based optimization, DecT can be trained within several seconds and requires only one P query per sample. We conduct extensive natural language understanding experiments and show that DecT significantly outperforms state-of-the-art algorithms with a $200times$ speed-up.
  arXiv  Detail & Related papers  (2022-12-16T11:15:39Z)
• Rapid Person Re-Identification via Sub-space Consistency Regularization [51.76876061721556]
  Person Re-Identification (ReID) matches pedestrians across disjoint cameras. Existing ReID methods adopting real-value feature descriptors have achieved high accuracy, but they are low in efficiency due to the slow Euclidean distance computation. We propose a novel Sub-space Consistency Regularization (SCR) algorithm that can speed up the ReID procedure by 0.25$ times.
  arXiv  Detail & Related papers  (2022-07-13T02:44:05Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)
• FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition [90.34177266618143]
  We propose FastCorrect, a novel NAR error correction model based on edit alignment. FastCorrect speeds up the inference by 6-9 times and maintains the accuracy (8-14% WER reduction) compared with the autoregressive correction model. It outperforms the accuracy of popular NAR models adopted in neural machine translation by a large margin.
  arXiv  Detail & Related papers  (2021-05-09T05:35:36Z)
• Non-Autoregressive Transformer ASR with CTC-Enhanced Decoder Input [54.82369261350497]
  We propose a CTC-enhanced NAR transformer, which generates target sequence by refining predictions of the CTC module. Experimental results show that our method outperforms all previous NAR counterparts and achieves 50x faster decoding speed than a strong AR baseline with only 0.0 0.3 absolute CER degradation on Aishell-1 and Aishell-2 datasets.
  arXiv  Detail & Related papers  (2020-10-28T15:00:09Z)
• Streaming automatic speech recognition with the transformer model [59.58318952000571]
  We propose a transformer based end-to-end ASR system for streaming ASR. We apply time-restricted self-attention for the encoder and triggered attention for the encoder-decoder attention mechanism. Our proposed streaming transformer architecture achieves 2.8% and 7.2% WER for the "clean" and "other" test data of LibriSpeech.
  arXiv  Detail & Related papers  (2020-01-08T18:58:02Z)

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.