English
Related papers

Related papers: End-to-End Training Approaches for Discriminative …

200 papers

Recently there has been significant interest in training machine-learning models at low precision: by reducing precision, one can reduce computation and communication by one order of magnitude. We examine training at reduced precision, both…

Machine Learning · Computer Science 2017-06-20 Hantian Zhang , Jerry Li , Kaan Kara , Dan Alistarh , Ji Liu , Ce Zhang

Deep learning models are often deployed in downstream tasks that the training procedure may not be aware of. For example, models solely trained to achieve accurate predictions may struggle to perform well on downstream tasks because…

Machine Learning · Computer Science 2024-09-27 Dishank Bansal , Ricky T. Q. Chen , Mustafa Mukadam , Brandon Amos

The idea of end-to-end learning of communication systems through neural network-based autoencoders has the shortcoming that it requires a differentiable channel model. We present in this paper a novel learning algorithm which alleviates…

Information Theory · Computer Science 2019-07-02 Fayçal Ait Aoudia , Jakob Hoydis

Recent achievements in end-to-end deep learning have encouraged the exploration of tasks dealing with highly structured data with unified deep network models. Having such models for compressing audio signals has been challenging since it…

Machine Learning · Computer Science 2021-07-14 Daniela N. Rim , Inseon Jang , Heeyoul Choi

Whereas conventional spoken language understanding (SLU) systems map speech to text, and then text to intent, end-to-end SLU systems map speech directly to intent through a single trainable model. Achieving high accuracy with these…

Audio and Speech Processing · Electrical Eng. & Systems 2019-07-26 Loren Lugosch , Mirco Ravanelli , Patrick Ignoto , Vikrant Singh Tomar , Yoshua Bengio

Filter pruning and low-rank decomposition are two of the foundational techniques for structured compression. Although recent efforts have explored hybrid approaches aiming to integrate the advantages of both techniques, their performance…

Machine Learning · Computer Science 2023-09-26 Moonjung Eo , Suhyun Kang , Wonjong Rhee

Current vision language pretraining models are dominated by methods using region visual features extracted from object detectors. Given their good performance, the extract-then-process pipeline significantly restricts the inference speed…

Computer Vision and Pattern Recognition · Computer Science 2023-01-19 Xiaofeng Yang , Fayao Liu , Guosheng Lin

Depression remains a pressing global mental health issue, driving considerable research into AI-driven detection approaches. While pre-trained models, particularly speech self-supervised models (SSL Models), have been applied to depression…

Audio and Speech Processing · Electrical Eng. & Systems 2025-03-11 Xiangyu Zhang , Beena Ahmed , Julien Epps

Deep neural networks often rely on spurious features to make predictions, which makes them brittle under distribution shift and on samples where the spurious correlation does not hold (e.g., minority-group examples). Recent studies have…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Aryan Yazdan Parast , Khawar Islam , Soyoun Won , Basim Azam , Naveed Akhtar

Conventional decision trees have a number of favorable properties, including interpretability, a small computational footprint and the ability to learn from little training data. However, they lack a key quality that has helped fuel the…

Machine Learning · Statistics 2017-12-08 Thomas Hehn , Fred A. Hamprecht

End-to-end attention-based models have been shown to be competitive alternatives to conventional DNN-HMM models in the Speech Recognition Systems. In this paper, we extend existing end-to-end attention-based models that can be applied for…

Computation and Language · Computer Science 2016-10-19 Hassan Taherian

Recent deep learning based approaches have shown remarkable success on object segmentation tasks. However, there is still room for further improvement. Inspired by generative adversarial networks, we present a generic end-to-end adversarial…

Computer Vision and Pattern Recognition · Computer Science 2019-09-24 Ricard Durall , Franz-Josef Pfreundt , Ullrich Köthe , Janis Keuper

Attention mechanism in sequence-to-sequence models is designed to model the alignments between acoustic features and output tokens in speech recognition. However, attention weights produced by models trained end to end do not always…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-27 Gene-Ping Yang , Hao Tang

This study systematically investigates two multi-fidelity strategies used to train machine-learned force fields (MLFFs) -- pre-training/fine-tuning and multi-headed training -- and elucidates the mechanisms underpinning their success. For…

Chemical Physics · Physics 2026-04-03 John L. A. Gardner , Hannes Schulz , Jean Helie , Lixin Sun , Gregor N. C. Simm

Continual Learning, also known as Lifelong Learning, aims to continually learn from new data as it becomes available. While prior research on continual learning in automatic speech recognition has focused on the adaptation of models across…

Machine Learning · Computer Science 2022-07-13 Muqiao Yang , Ian Lane , Shinji Watanabe

Recently, attempts have been made to remove Gaussian mixture models (GMM) from the training process of deep neural network-based hidden Markov models (HMM/DNN). For the GMM-free training of a HMM/DNN hybrid we have to solve two problems,…

Computation and Language · Computer Science 2016-10-18 Gábor Gosztolya , Tamás Grósz , László Tóth

End-to-end Large Speech Language Models (LSLMs) have demonstrated impressive conversational generation abilities, yet consistently fall short of traditional pipeline systems on semantic understanding benchmarks. In this work, we reveal…

Computation and Language · Computer Science 2025-10-15 Bajian Xiang , Shuaijiang Zhao , Tingwei Guo , Wei Zou

End-to-end models are gaining wider attention in the field of automatic speech recognition (ASR). One of their advantages is the simplicity of building that directly recognizes the speech frame sequence into the text label sequence by…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-26 Linhao Dong , Cheng Yi , Jianzong Wang , Shiyu Zhou , Shuang Xu , Xueli Jia , Bo Xu

Training Large Language Models (LLMs) typically involves a two-stage pipeline at the output layer: hidden states are projected into vocabulary logits via a linear transformation (lm_head), followed by cross-entropy loss computation against…

Machine Learning · Computer Science 2025-11-25 Jianbing Dong , Jianbin Chang

End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-19 Ankur Gandhe , Ariya Rastrow