Towards Maximum Likelihood Training for Transducer-based Streaming Speech Recognition

• URL: http://arxiv.org/abs/2411.17537v1
• Date: Tue, 26 Nov 2024 15:53:13 GMT
• Title: Towards Maximum Likelihood Training for Transducer-based Streaming Speech Recognition
• Authors: Hyeonseung Lee, Ji Won Yoon, Sungsoo Kim, Nam Soo Kim,
• Abstract summary: We present a new approach for streaming automatic speech recognition (ASR) using transducer neural networks. In the conventional framework, streaming transducer models are trained to maximize the likelihood function based on non-streaming recursion rules. We show that FoCCE training improves the accuracy of the streaming transducers.
• Score: 13.189571090038674
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transducer neural networks have emerged as the mainstream approach for streaming automatic speech recognition (ASR), offering state-of-the-art performance in balancing accuracy and latency. In the conventional framework, streaming transducer models are trained to maximize the likelihood function based on non-streaming recursion rules. However, this approach leads to a mismatch between training and inference, resulting in the issue of deformed likelihood and consequently suboptimal ASR accuracy. We introduce a mathematical quantification of the gap between the actual likelihood and the deformed likelihood, namely forward variable causal compensation (FoCC). We also present its estimator, FoCCE, as a solution to estimate the exact likelihood. Through experiments on the LibriSpeech dataset, we show that FoCCE training improves the accuracy of the streaming transducers.

Related papers

• Joint Source-Channel-Generation Coding: From Distortion-oriented Reconstruction to Semantic-consistent Generation [58.67925548779465]
  We propose Joint Source-Channel-Generation Coding (JSCGC), a novel paradigm that shifts the focus from perceptual reconstruction to probabilistic generation.<n>JSCGC improves substantially semantic quality and semantic fidelity, significantly outperforming conventional distortion-oriented J SCC methods.
  arXiv  Detail & Related papers  (2026-01-19T08:12:47Z)
• Drax: Speech Recognition with Discrete Flow Matching [26.991421132974097]
  Diffusion and flow-based non-autoregressive (NAR) models have shown strong promise in large language modeling.<n>We propose Drax, a discrete flow matching framework for automatic speech recognition (ASR)<n>We construct an audio-conditioned probability path that guides the model through trajectories resembling likely intermediate inference errors.
  arXiv  Detail & Related papers  (2025-10-05T11:38:01Z)
• Confidence Optimization for Probabilistic Encoding [0.9999629695552196]
  We introduce a confidence-aware mechanism to adjust distance calculations.<n>We replace the conventional KL divergence-based variance regularization with a simpler L2 regularization term to directly constrain variance.<n>Our method significantly improves performance and generalization on both the BERT and the RoBERTa model.
  arXiv  Detail & Related papers  (2025-07-22T15:32:27Z)
• Solving Inverse Problems with FLAIR [68.87167940623318]
  We present FLAIR, a training-free variational framework that leverages flow-based generative models as prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• Efficient Test-time Adaptive Object Detection via Sensitivity-Guided Pruning [73.40364018029673]
  Continual test-time adaptive object detection (CTTA-OD) aims to online adapt a source pre-trained detector to ever-changing environments.<n>Our motivation stems from the observation that not all learned source features are beneficial.<n>Our method achieves superior adaptation performance while reducing computational overhead by 12% in FLOPs.
  arXiv  Detail & Related papers  (2025-06-03T05:27:56Z)
• Directly Attention Loss Adjusted Prioritized Experience Replay [0.07366405857677226]
  Prioritized Replay Experience (PER) enables the model to learn more about relatively important samples by artificially changing their accessed frequencies. DALAP is proposed, which can directly quantify the changed extent of the shifted distribution through Parallel Self-Attention network.
  arXiv  Detail & Related papers  (2023-11-24T10:14:05Z)
• Observation-Guided Diffusion Probabilistic Models [41.749374023639156]
  We propose a novel diffusion-based image generation method called the observation-guided diffusion probabilistic model (OGDM) Our approach reestablishes the training objective by integrating the guidance of the observation process with the Markov chain. We demonstrate the effectiveness of our training algorithm using diverse inference techniques on strong diffusion model baselines.
  arXiv  Detail & Related papers  (2023-10-06T06:29:06Z)
• Adaptive mitigation of time-varying quantum noise [0.1227734309612871]
  Current quantum computers suffer from non-stationary noise channels with high error rates. We propose a Bayesian inference-based adaptive algorithm that can learn and mitigate quantum noise in response to changing channel conditions.
  arXiv  Detail & Related papers  (2023-08-16T01:33:07Z)
• Exploiting Diffusion Prior for Real-World Image Super-Resolution [75.5898357277047]
  We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution. By employing our time-aware encoder, we can achieve promising restoration results without altering the pre-trained synthesis model.
  arXiv  Detail & Related papers  (2023-05-11T17:55:25Z)
• Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer [60.31021888394358]
  Unsupervised Domain Adaptation (UDA) can effectively address domain gap issues in real-world image Super-Resolution (SR) We propose a SOurce-free Domain Adaptation framework for image SR (SODA-SR) to address this issue, i.e., adapt a source-trained model to a target domain with only unlabeled target data.
  arXiv  Detail & Related papers  (2023-03-31T03:14:44Z)
• Denoising Diffusion Autoencoders are Unified Self-supervised Learners [58.194184241363175]
  This paper shows that the networks in diffusion models, namely denoising diffusion autoencoders (DDAE), are unified self-supervised learners. DDAE has already learned strongly linear-separable representations within its intermediate layers without auxiliary encoders. Our diffusion-based approach achieves 95.9% and 50.0% linear evaluation accuracies on CIFAR-10 and Tiny-ImageNet.
  arXiv  Detail & Related papers  (2023-03-17T04:20:47Z)
• Direction-Aware Adaptive Online Neural Speech Enhancement with an Augmented Reality Headset in Real Noisy Conversational Environments [21.493664174262737]
  This paper describes the practical response- and performance-aware development of online speech enhancement for an augmented reality (AR) headset. It helps a user understand conversations made in real noisy echoic environments (e.g., cocktail party) The method is used with a blind dereverberation method called weighted prediction error (WPE) for transcribing the noisy reverberant speech of a speaker.
  arXiv  Detail & Related papers  (2022-07-15T05:14:27Z)
• A Variational Bayesian Approach to Learning Latent Variables for Acoustic Knowledge Transfer [55.20627066525205]
  We propose a variational Bayesian (VB) approach to learning distributions of latent variables in deep neural network (DNN) models. Our proposed VB approach can obtain good improvements on target devices, and consistently outperforms 13 state-of-the-art knowledge transfer algorithms.
  arXiv  Detail & Related papers  (2021-10-16T15:54:01Z)
• A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systems [42.05399301143457]
  We introduce a light-weight contextual spelling correction model to correct context-related recognition errors. Experiments show that the model improves baseline ASR model performance with about 50% relative word error rate reduction. The model also shows excellent performance for out-of-vocabulary terms not seen during training.
  arXiv  Detail & Related papers  (2021-08-17T08:14:37Z)
• Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training [55.824641135682725]
  Domain adaptation experiments using WSJ as a source domain and TED-LIUM 3 as well as SWITCHBOARD show that up to 80% of the performance of a system trained on ground-truth data can be recovered.
  arXiv  Detail & Related papers  (2020-11-26T18:51:26Z)
• Uncertainty Estimation Using a Single Deep Deterministic Neural Network [66.26231423824089]
  We propose a method for training a deterministic deep model that can find and reject out of distribution data points at test time with a single forward pass. We scale training in these with a novel loss function and centroid updating scheme and match the accuracy of softmax models.
  arXiv  Detail & Related papers  (2020-03-04T12:27:36Z)

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.