Boosting Hybrid Autoregressive Transducer-based ASR with Internal Acoustic Model Training and Dual Blank Thresholding

• URL: http://arxiv.org/abs/2409.20313v1
• Date: Mon, 30 Sep 2024 14:14:45 GMT
• Title: Boosting Hybrid Autoregressive Transducer-based ASR with Internal Acoustic Model Training and Dual Blank Thresholding
• Abstract summary: Internal acoustic model (IAM) training strategy to enhance HAT-based speech recognition. IAM consists of encoder and joint networks, which are fully shared and jointly trained with HAT.
• Score: 35.29443802809237
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: A hybrid autoregressive transducer (HAT) is a variant of neural transducer that models blank and non-blank posterior distributions separately. In this paper, we propose a novel internal acoustic model (IAM) training strategy to enhance HAT-based speech recognition. IAM consists of encoder and joint networks, which are fully shared and jointly trained with HAT. This joint training not only enhances the HAT training efficiency but also encourages IAM and HAT to emit blanks synchronously which skips the more expensive non-blank computation, resulting in more effective blank thresholding for faster decoding. Experiments demonstrate that the relative error reductions of the HAT with IAM compared to the vanilla HAT are statistically significant. Moreover, we introduce dual blank thresholding, which combines both HAT- and IAM-blank thresholding and a compatible decoding algorithm. This results in a 42-75% decoding speed-up with no major performance degradation.

Related papers

• DiffusionGemma Technical Report [72.10570774996219]
  We introduce DiffusionGemma, a language model that uses discrete diffusion to generate text at exceptionally high speed.<n>Rather than decoding one token at a time, DiffusionGemma iteratively refines blocks of 256 tokens in parallel.<n>Our compute-efficient two-stage training pipeline uses fewer than 10% of the starting AR model's total training token budget.
  arXiv  Detail & Related papers  (2026-07-31T16:11:46Z)
• SATB-VR: Training Few-Step Video Restoration Diffusion Model using SNR-Aware Trajectory Blending [55.764018145256216]
  We present SATB-VR, a few-step paradigm that jump-starts the denoising process via an auxiliary predictor.<n>We show that SATB-VR performs favorably against existing approaches on synthetic, real-world, and AIGC benchmarks.
  arXiv  Detail & Related papers  (2026-06-27T01:32:16Z)
• FLARE: Diffusion for Hybrid Language Model [72.60770374799634]
  FLARE is a systematic conversion framework for hybrid-attention large language models.<n>It combines a token-equal AR-and-diffusion objective, hardware-aware kernels, and unified inference, enabling one checkpoint to support both AR-style verified decoding and diffusion-style parallel denoising.<n>Our results suggest practical dLLMs are limited not only by decoding algorithms, but also by transfer data quality and the training inefficiency of current block-diffusion objectives.
  arXiv  Detail & Related papers  (2026-06-01T06:58:15Z)
• SimReg: Achieving Higher Performance in the Pretraining via Embedding Similarity Regularization [55.63565289584336]
  SimReg is an embedding similarity regularization loss that explicitly encourages token representations with the same ground-truth label within each sequence to be more similar.<n>Our analysis reveals that this mechanism introduces gains by enlarging multi-classification margins, thereby enabling more efficient classification.
  arXiv  Detail & Related papers  (2026-05-09T08:59:13Z)
• GFRRN: Explore the Gaps in Single Image Reflection Removal [23.018215754935753]
  We propose a Gap-Free Reflection Removal Network (GFRRN) for single image reflection removal.<n>In this work, we first adopt the parameter efficient fine-tuning (PEFT) strategy to align the training directions.<n>Then, a label generator is designed to unify the reflection labels for both synthetic and real-world data.<n>Extensive experiments demonstrate the effectiveness of our GFRRN, achieving superior performance against state-of-the-art SIRR methods.
  arXiv  Detail & Related papers  (2026-02-26T07:17:49Z)
• VAE-REPA: Variational Autoencoder Representation Alignment for Efficient Diffusion Training [53.09658039757408]
  This paper proposes textbfnamex, a lightweight intrinsic guidance framework for efficient diffusion training.<n>name aligns the intermediate latent features of diffusion transformers with VAE features via a lightweight projection layer, supervised by a feature alignment loss.<n>Experiments demonstrate that name improves both generation quality and training convergence speed compared to vanilla diffusion transformers.
  arXiv  Detail & Related papers  (2026-01-25T13:22:38Z)
• Faster WIND: Accelerating Iterative Best-of-$N$ Distillation for LLM Alignment [81.84950252537618]
  This paper reveals a unified game-theoretic connection between iterative BOND and self-play alignment. We establish a novel framework, WIN rate Dominance (WIND), with a series of efficient algorithms for regularized win rate dominance optimization.
  arXiv  Detail & Related papers  (2024-10-28T04:47:39Z)
• Three-in-One: Fast and Accurate Transducer for Hybrid-Autoregressive ASR [17.950722198543897]
  We present textbfHybrid-textbfAutoregressive textbfINference TrtextbfANsducers (HAINAN), a novel architecture for speech recognition. HAINAN supports both autoregressive inference with all network components and non-autoregressive inference without the predictor.
  arXiv  Detail & Related papers  (2024-10-03T15:38:20Z)
• Covariance-corrected Whitening Alleviates Network Degeneration on Imbalanced Classification [6.197116272789107]
  Class imbalance is a critical issue in image classification that significantly affects the performance of deep recognition models. We propose a novel framework called Whitening-Net to mitigate the degenerate solutions. In scenarios with extreme class imbalance, the batch covariance statistic exhibits significant fluctuations, impeding the convergence of the whitening operation.
  arXiv  Detail & Related papers  (2024-08-30T10:49:33Z)
• Mutual Learning for Acoustic Matching and Dereverberation via Visual Scene-driven Diffusion [93.32354378820648]
  We introduce MVSD, a mutual learning framework based on diffusion models. MVSD considers the two tasks symmetrically, exploiting the reciprocal relationship to facilitate learning from inverse tasks. Our framework can improve the performance of the reverberator and dereverberator.
  arXiv  Detail & Related papers  (2024-07-15T00:47:56Z)
• DASA: Difficulty-Aware Semantic Augmentation for Speaker Verification [55.306583814017046]
  We present a novel difficulty-aware semantic augmentation (DASA) approach for speaker verification. DASA generates diversified training samples in speaker embedding space with negligible extra computing cost. The best result achieves a 14.6% relative reduction in EER metric on CN-Celeb evaluation set.
  arXiv  Detail & Related papers  (2023-10-18T17:07:05Z)
• Modular Hybrid Autoregressive Transducer [51.29870462504761]
  Text-only adaptation of a transducer model remains challenging for end-to-end speech recognition. We propose a modular hybrid autoregressive transducer that has structurally separated label and blank decoders. On Google's large-scale production data, a multi-domain MHAT adapted with 100B sentences achieves relative WER reductions of up to 12.4% without LM fusion.
  arXiv  Detail & Related papers  (2022-10-31T03:56:37Z)
• Integrate Lattice-Free MMI into End-to-End Speech Recognition [87.01137882072322]
  In automatic speech recognition (ASR) research, discriminative criteria have achieved superior performance in DNN-HMM systems. With this motivation, the adoption of discriminative criteria is promising to boost the performance of end-to-end (E2E) ASR systems. Previous works have introduced the minimum Bayesian risk (MBR, one of the discriminative criteria) into E2E ASR systems. In this work, novel algorithms are proposed in this work to integrate another widely used discriminative criterion, lattice-free maximum mutual information (LF-MMI) into E2E
  arXiv  Detail & Related papers  (2022-03-29T14:32:46Z)
• Improving Hybrid CTC/Attention End-to-end Speech Recognition with Pretrained Acoustic and Language Model [4.490054848527943]
  We propose a pretrained Transformer (Preformer) S2S ASR architecture based on hybrid CTC/attention E2E models. To the best of our knowledge, this is the first work to utilize both pretrained AM and LM in a S2S ASR system.
  arXiv  Detail & Related papers  (2021-12-14T09:38:31Z)
• A Mixture of Expert Based Deep Neural Network for Improved ASR [4.993304210475779]
  MixNet is a novel deep learning architecture for acoustic model in the context of Automatic Speech Recognition (ASR) In natural speech, overlap in distribution across different acoustic classes is inevitable, which leads to inter-class mis-classification. Experiments are conducted on a large vocabulary ASR task which show that the proposed architecture provides 13.6% and 10.0% relative reduction in word error rates.
  arXiv  Detail & Related papers  (2021-12-02T07:26:34Z)
• On Minimum Word Error Rate Training of the Hybrid Autoregressive Transducer [40.63693071222628]
  We study the minimum word error rate (MWER) training of Hybrid Autoregressive Transducer (HAT) From experiments with around 30,000 hours of training data, we show that MWER training can improve the accuracy of HAT models.
  arXiv  Detail & Related papers  (2020-10-23T21:16:30Z)

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.