Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR

• URL: http://arxiv.org/abs/2004.05009v2
• Date: Fri, 15 May 2020 00:21:37 GMT
• Title: Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR
• Authors: Hirofumi Inaguma, Yashesh Gaur, Liang Lu, Jinyu Li, Yifan Gong
• Abstract summary: Streaming attention-based sequence-to-sequence (S2S) models have been proposed to perform online speech recognition with linear-time decoding complexity. In these models, the decisions to generate tokens are delayed compared to the actual acoustic boundaries since their unidirectional encoders lack future information. We propose several strategies during training by leveraging external hard alignments extracted from the hybrid model. Experiments on the Cortana voice search task demonstrate that our proposed methods can significantly reduce the latency, and even improve the recognition accuracy in certain cases on the decoder side.
• Score: 44.229256049718316
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, a few novel streaming attention-based sequence-to-sequence (S2S) models have been proposed to perform online speech recognition with linear-time decoding complexity. However, in these models, the decisions to generate tokens are delayed compared to the actual acoustic boundaries since their unidirectional encoders lack future information. This leads to an inevitable latency during inference. To alleviate this issue and reduce latency, we propose several strategies during training by leveraging external hard alignments extracted from the hybrid model. We investigate to utilize the alignments in both the encoder and the decoder. On the encoder side, (1) multi-task learning and (2) pre-training with the framewise classification task are studied. On the decoder side, we (3) remove inappropriate alignment paths beyond an acceptable latency during the alignment marginalization, and (4) directly minimize the differentiable expected latency loss. Experiments on the Cortana voice search task demonstrate that our proposed methods can significantly reduce the latency, and even improve the recognition accuracy in certain cases on the decoder side. We also present some analysis to understand the behaviors of streaming S2S models.

Related papers

• DEER: A Delay-Resilient Framework for Reinforcement Learning with Variable Delays [26.032139258562708]
  We propose $textbfDEER (Delay-resilient-Enhanced RL)$, a framework designed to effectively enhance the interpretability and address the random delay issues. In a variety of delayed scenarios, the trained encoder can seamlessly integrate with standard RL algorithms without requiring additional modifications. The results confirm that DEER is superior to state-of-the-art RL algorithms in both constant and random delay settings.
  arXiv  Detail & Related papers  (2024-06-05T09:45:26Z)
• Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference [95.42299246592756]
  We study the UNet encoder and empirically analyze the encoder features. We find that encoder features change minimally, whereas the decoder features exhibit substantial variations across different time-steps. We validate our approach on other tasks: text-to-video, personalized generation and reference-guided generation.
  arXiv  Detail & Related papers  (2023-12-15T08:46:43Z)
• Short-Term Memory Convolutions [0.0]
  We propose novel method for minimization of inference time latency and memory consumption, called Short-Term Memory Convolution (STMC) The training of STMC-based models is faster and more stable as the method is based solely on convolutional neural networks (CNNs) In case of speech separation we achieved a 5-fold reduction in inference time and a 2-fold reduction in latency without affecting the output quality.
  arXiv  Detail & Related papers  (2023-02-08T20:52:24Z)
• Minimum Latency Training of Sequence Transducers for Streaming End-to-End Speech Recognition [38.28868751443619]
  We propose a new training method to explicitly model and reduce the latency of sequence transducer models. Experimental results show that the proposed minimum latency training reduces the latency of causal Conformer-T from 220 ms to 27 ms within a WER degradation of 0.7%.
  arXiv  Detail & Related papers  (2022-11-04T09:19:59Z)
• Streaming Align-Refine for Non-autoregressive Deliberation [42.748839817396046]
  We propose a streaming non-autoregressive (non-AR) decoding algorithm to deliberate the hypothesis alignment of a streaming RNN-T model. Our algorithm facilitates a simple greedy decoding procedure, and at the same time is capable of producing the decoding result at each frame with limited right context. Experiments on voice search datasets and Librispeech show that with reasonable right context, our streaming model performs as well as the offline counterpart.
  arXiv  Detail & Related papers  (2022-04-15T17:24:39Z)
• Streaming parallel transducer beam search with fast-slow cascaded encoders [23.416682253435837]
  Streaming and non-streaming ASR for RNN Transducers can be unified by cascading causal and non-causal encoders. We propose a novel parallel time-synchronous beam search algorithm for transducers that decodes from fast-slow encoders.
  arXiv  Detail & Related papers  (2022-03-29T17:29:39Z)
• Real-Time GPU-Accelerated Machine Learning Based Multiuser Detection for 5G and Beyond [70.81551587109833]
  nonlinear beamforming filters can significantly outperform linear approaches in stationary scenarios with massive connectivity. One of the main challenges comes from the real-time implementation of these algorithms. This paper explores the acceleration of APSM-based algorithms through massive parallelization.
  arXiv  Detail & Related papers  (2022-01-13T15:20:45Z)
• Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization [96.73647162960842]
  TAL is a fundamental yet challenging task in video understanding. Existing TAL methods rely on pre-training a video encoder through action classification supervision. We introduce a novel low-fidelity end-to-end (LoFi) video encoder pre-training method.
  arXiv  Detail & Related papers  (2021-03-28T22:18:14Z)
• Short-Term Memory Optimization in Recurrent Neural Networks by Autoencoder-based Initialization [79.42778415729475]
  We explore an alternative solution based on explicit memorization using linear autoencoders for sequences. We show how such pretraining can better support solving hard classification tasks with long sequences. We show that the proposed approach achieves a much lower reconstruction error for long sequences and a better gradient propagation during the finetuning phase.
  arXiv  Detail & Related papers  (2020-11-05T14:57:16Z)
• Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation [66.46123655365113]
  Target speech separation refers to extracting the target speaker's speech from mixed signals. Two main challenges are the complex acoustic environment and the real-time processing requirement. We propose a temporal-spatial neural filter, which directly estimates the target speech waveform from multi-speaker mixture.
  arXiv  Detail & Related papers  (2020-01-02T11:12:50Z)

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.