English
Related papers

Related papers: Regularized Forward-Backward Decoder for Attention…

200 papers

This work analyzes how attention-based Bidirectional Long Short-Term Memory (BLSTM) models adapt to noise-augmented speech. We identify crucial components for noise adaptation in BLSTM models by freezing model components during fine-tuning.…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-27 Coleman Hooper , Thierry Tambe , Gu-Yeon Wei

Regularization is important for end-to-end speech models, since the models are highly flexible and easy to overfit. Data augmentation and dropout has been important for improving end-to-end models in other domains. However, they are…

Computation and Language · Computer Science 2017-12-20 Yingbo Zhou , Caiming Xiong , Richard Socher

We compare the fast training and decoding speed of RETURNN of attention models for translation, due to fast CUDA LSTM kernels, and a fast pure TensorFlow beam search decoder. We show that a layer-wise pretraining scheme for recurrent…

Neural and Evolutionary Computing · Computer Science 2019-08-06 Albert Zeyer , Tamer Alkhouli , Hermann Ney

Recent psycholinguistic research has compared human reading times to surprisal estimates from language models to study the factors shaping human sentence processing difficulty. Previous studies have shown a strong fit between surprisal…

Computation and Language · Computer Science 2024-09-18 Christian Clark , Byung-Doh Oh , William Schuler

With the development of deep learning, neural network-based speech enhancement (SE) models have shown excellent performance. Meanwhile, it was shown that the development of self-supervised pre-trained models can be applied to various…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-29 Xiao-Ying Zhao , Qiu-Shi Zhu , Jie Zhang

We often use perturbations to regularize neural models. For neural encoder-decoders, previous studies applied the scheduled sampling (Bengio et al., 2015) and adversarial perturbations (Sato et al., 2019) as perturbations but these methods…

Computation and Language · Computer Science 2021-04-06 Sho Takase , Shun Kiyono

To join the advantages of classical and end-to-end approaches for speech recognition, we present a simple, novel and competitive approach for phoneme-based neural transducer modeling. Different alignment label topologies are compared and…

Computation and Language · Computer Science 2021-04-21 Wei Zhou , Simon Berger , Ralf Schlüter , Hermann Ney

This paper proposes a novel Attention-based Encoder-Decoder network for End-to-End Neural speaker Diarization (AED-EEND). In AED-EEND system, we incorporate the target speaker enrollment information used in target speaker voice activity…

Sound · Computer Science 2023-08-16 Zhengyang Chen , Bing Han , Shuai Wang , Yanmin Qian

Transformer-based architectures achieve state-of-the-art performance across a wide range of tasks in natural language processing, computer vision, and speech processing. However, their immense capacity often leads to overfitting, especially…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Mirza Samad Ahmed Baig , Syeda Anshrah Gillani , Abdul Akbar Khan , Shahid Munir Shah , Muhammad Omer Khan

Semantic segmentation labels are expensive and time consuming to acquire. Hence, pretraining is commonly used to improve the label-efficiency of segmentation models. Typically, the encoder of a segmentation model is pretrained as a…

Computer Vision and Pattern Recognition · Computer Science 2022-05-24 Emmanuel Brempong Asiedu , Simon Kornblith , Ting Chen , Niki Parmar , Matthias Minderer , Mohammad Norouzi

We address the problem of learning efficient and adaptive ways to communicate binary information over an impaired channel. We treat the problem as reconstruction optimization through impairment layers in a channel autoencoder and introduce…

Machine Learning · Computer Science 2016-08-24 Timothy J O'Shea , Kiran Karra , T. Charles Clancy

Language model (LM) pre-training has resulted in impressive performance and sample efficiency on a variety of language understanding tasks. However, it remains unclear how to best use pre-trained LMs for generation tasks such as abstractive…

Computation and Language · Computer Science 2019-05-23 Urvashi Khandelwal , Kevin Clark , Dan Jurafsky , Lukasz Kaiser

Neural front-ends are an appealing alternative to traditional, fixed feature extraction pipelines for automatic speech recognition (ASR) systems since they can be directly trained to fit the acoustic model. However, their performance often…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-01 Peter Vieting , Maximilian Kannen , Benedikt Hilmes , Ralf Schlüter , Hermann Ney

The transformer is the most popular neural architecture for language modeling. The cornerstone of the transformer is its global attention mechanism, which lets the model aggregate information from all preceding tokens before generating the…

Computation and Language · Computer Science 2026-05-20 Jiaoda Li , Ryan Cotterell

We introduce a novel segmental-attention model for automatic speech recognition. We restrict the decoder attention to segments to avoid quadratic runtime of global attention, better generalize to long sequences, and eventually enable…

Computation and Language · Computer Science 2022-10-27 Albert Zeyer , Robin Schmitt , Wei Zhou , Ralf Schlüter , Hermann Ney

We propose an attention-enabled encoder-decoder model for the problem of grapheme-to-phoneme conversion. Most previous work has tackled the problem via joint sequence models that require explicit alignments for training. In contrast, the…

Computation and Language · Computer Science 2016-10-21 Shubham Toshniwal , Karen Livescu

In this paper, we propose a simple and effective technique to allow for efficient self-supervised learning with bi-directional Transformers. Our approach is motivated by recent studies demonstrating that self-attention patterns in trained…

Computation and Language · Computer Science 2020-10-07 Ameet Deshpande , Karthik Narasimhan

We introduce an online neural sequence to sequence model that learns to alternate between encoding and decoding segments of the input as it is read. By independently tracking the encoding and decoding representations our algorithm permits…

Computation and Language · Computer Science 2016-09-28 Lei Yu , Jan Buys , Phil Blunsom

Transformer network architecture has proven effective in speech enhancement. However, as its core module, self-attention suffers from quadratic complexity, making it infeasible for training on long speech utterances. In practical scenarios,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-10 Qiquan Zhang , Hongxu Zhu , Xinyuan Qian , Eliathamby Ambikairajah , Haizhou Li

Attention encoder-decoder model architecture is the backbone of several recent top performing foundation speech models: Whisper, Seamless, OWSM, and Canary-1B. However, the reported data and compute requirements for their training are…

‹ Prev 1 3 4 5 6 7 10 Next ›