English
Related papers

Related papers: Memory-Efficient Training of RNN-Transducer with S…

200 papers

In this paper, we share our reflections and insights on understanding Transformer architectures through the lens of associative memory--a classic psychological concept inspired by human cognition. We start with the basics of associative…

Machine Learning · Computer Science 2025-05-27 Shu Zhong , Mingyu Xu , Tenglong Ao , Guang Shi

Recurrent Neural Networks (RNNs) are powerful models for sequential data that have the potential to learn long-term dependencies. However, they are computationally expensive to train and difficult to parallelize. Recent work has shown that…

Machine Learning · Statistics 2015-10-07 César Laurent , Gabriel Pereyra , Philémon Brakel , Ying Zhang , Yoshua Bengio

Negative transfer in training of acoustic models for automatic speech recognition has been reported in several contexts such as domain change or speaker characteristics. This paper proposes a novel technique to overcome negative transfer by…

Machine Learning · Computer Science 2015-09-18 Mortaza Doulaty , Oscar Saz , Thomas Hain

Despite the significant progress made in the last years, state-of-the-art speech recognition technologies provide a satisfactory performance only in the close-talking condition. Robustness of distant speech recognition in adverse acoustic…

Audio and Speech Processing · Electrical Eng. & Systems 2017-10-11 Mirco Ravanelli , Maurizio Omologo

Spatiotemporal predictive learning, which predicts future frames through historical prior knowledge with the aid of deep learning, is widely used in many fields. Previous work essentially improves the model performance by widening or…

Computer Vision and Pattern Recognition · Computer Science 2024-03-01 Zhifeng Ma , Hao Zhang , Jie Liu

Compared to monolingual models, cross-lingual models usually require a more expressive vocabulary to represent all languages adequately. We find that many languages are under-represented in recent cross-lingual language models due to the…

Computation and Language · Computer Science 2021-09-16 Bo Zheng , Li Dong , Shaohan Huang , Saksham Singhal , Wanxiang Che , Ting Liu , Xia Song , Furu Wei

We present an architecture of a recurrent neural network (RNN) with a fully-connected deep neural network (DNN) as its feature extractor. The RNN is equipped with both causal temporal prediction and non-causal look-ahead, via…

Machine Learning · Computer Science 2014-03-07 Jianshu Chen , Li Deng

With the popularity of deep neural network, speech synthesis task has achieved significant improvements based on the end-to-end encoder-decoder framework in the recent days. More and more applications relying on speech synthesis technology…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-23 Dongyang Dai , Li Chen , Yuping Wang , Mu Wang , Rui Xia , Xuchen Song , Zhiyong Wu , Yuxuan Wang

Soft prompt tuning is a parameter-efficient method for adapting LLMs to specific tasks, but suffers from a lack of interpretability. Building on recent work on interpreting soft prompts (Ramati et al., 2024), we explore how training a…

Computation and Language · Computer Science 2026-05-28 Pitipat Kongsomjit , Suryansh Goyal , Jacob Whitehill

Self-supervised learning has been proved to benefit a wide range of speech processing tasks, such as speech recognition/translation, speaker verification and diarization, etc. However, most of current approaches are computationally…

RNN-Transducer (RNN-T) is a widely adopted architecture in speech recognition, integrating acoustic and language modeling in an end-to-end framework. However, the RNN-T predictor tends to over-rely on consecutive word dependencies in…

Sound · Computer Science 2025-02-21 Khanh Le , Tuan Vu Ho , Dung Tran , Duc Thanh Chau

The self-attention mechanism distinguishes transformer-based large language models (LLMs) apart from convolutional and recurrent neural networks. Despite the performance improvement, achieving real-time LLM inference on silicon remains…

Hardware Architecture · Computer Science 2024-11-18 Shiwei Liu , Guanchen Tao , Yifei Zou , Derek Chow , Zichen Fan , Kauna Lei , Bangfei Pan , Dennis Sylvester , Gregory Kielian , Mehdi Saligane

To encourage intra-class compactness and inter-class separability among trainable feature vectors, large-margin softmax methods are developed and widely applied in the face recognition community. The introduction of the large-margin concept…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-22 Jingjing Huo , Yingbo Gao , Weiyue Wang , Ralf Schlüter , Hermann Ney

Recurrent Neural Networks (RNNs) are powerful tools for solving sequence-based problems, but their efficacy and execution time are dependent on the size of the network. Following recent work in simplifying these networks with model pruning…

Neural and Evolutionary Computing · Computer Science 2018-04-30 Feiwen Zhu , Jeff Pool , Michael Andersch , Jeremy Appleyard , Fung Xie

Transformer models have been introduced into end-to-end speech recognition with state-of-the-art performance on various tasks owing to their superiority in modeling long-term dependencies. However, such improvements are usually obtained…

Sound · Computer Science 2020-11-18 Haoneng Luo , Shiliang Zhang , Ming Lei , Lei Xie

Speech transcription, emotion recognition, and language identification are usually considered to be three different tasks. Each one requires a different model with a different architecture and training process. We propose using a recurrent…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-29 Zvi Kons , Hagai Aronowitz , Edmilson Morais , Matheus Damasceno , Hong-Kwang Kuo , Samuel Thomas , George Saon

Recently, language identity information has been utilized to improve the performance of end-to-end code-switching (CS) speech recognition. However, previous works use an additional language identification (LID) model as an auxiliary module,…

Computation and Language · Computer Science 2020-02-20 Shuai Zhang , Jiangyan Yi , Zhengkun Tian , Jianhua Tao , Ye Bai

Various forms of sparse attention have been explored to mitigate the quadratic computational and memory cost of the attention mechanism in transformers. We study sparse transformers not through a lens of efficiency but rather in terms of…

Machine Learning · Computer Science 2025-06-19 Parikshit Ram , Kenneth L. Clarkson , Tim Klinger , Shashanka Ubaru , Alexander G. Gray

In neural machine translation (NMT), the computational cost at the output layer increases with the size of the target-side vocabulary. Using a limited-size vocabulary instead may cause a significant decrease in translation quality. This…

Computation and Language · Computer Science 2018-07-31 Katsuki Chousa , Katsuhito Sudoh , Satoshi Nakamura

Automatic Speech Recognition (ASR) based on Recurrent Neural Network Transducers (RNN-T) is gaining interest in the speech community. We investigate data selection and preparation choices aiming for improved robustness of RNN-T ASR to…

Computation and Language · Computer Science 2020-12-14 Valentin Mendelev , Tina Raissi , Guglielmo Camporese , Manuel Giollo