English
Related papers

Related papers: Streaming Transformer Transducer Based Speech Reco…

200 papers

This paper presents a new network architecture called multi-head decoder for end-to-end speech recognition as an extension of a multi-head attention model. In the multi-head attention model, multiple attentions are calculated, and then,…

Computation and Language · Computer Science 2018-07-31 Tomoki Hayashi , Shinji Watanabe , Tomoki Toda , Kazuya Takeda

It's challenging to customize transducer-based automatic speech recognition (ASR) system with context information which is dynamic and unavailable during model training. In this work, we introduce a light-weight contextual spelling…

Computation and Language · Computer Science 2021-08-29 Xiaoqiang Wang , Yanqing Liu , Sheng Zhao , Jinyu Li

In the slot-filling paradigm, where a user can refer back to slots in the context during the conversation, the goal of the contextual understanding system is to resolve the referring expressions to the appropriate slots in the context. In…

Computation and Language · Computer Science 2018-11-28 Amr Sharaf , Arpit Gupta , Hancheng Ge , Chetan Naik , Lambert Mathias

Since 2017, the Transformer-based models play critical roles in various downstream Natural Language Processing tasks. However, a common limitation of the attention mechanism utilized in Transformer Encoder is that it cannot automatically…

Computation and Language · Computer Science 2022-04-20 Ziyang Luo , Yadong Xi , Jing Ma , Zhiwei Yang , Xiaoxi Mao , Changjie Fan , Rongsheng Zhang

Transformer hugely benefits from its key design of the multi-head self-attention network (SAN), which extracts information from various perspectives through transforming the given input into different subspaces. However, its simple linear…

Computation and Language · Computer Science 2020-05-01 Sufeng Duan , Juncheng Cao , Hai Zhao

Unneeded elements in the attention's context degrade performance. We introduce Selective Attention, a simple parameter-free change to the standard attention mechanism which reduces attention to unneeded elements. Selective attention…

Computation and Language · Computer Science 2025-04-25 Yaniv Leviathan , Matan Kalman , Yossi Matias

Conformer-based end-to-end models have become ubiquitous these days and are commonly used in both streaming and non-streaming automatic speech recognition (ASR). Techniques like dual-mode and dynamic chunk training helped unify streaming…

Audio and Speech Processing · Electrical Eng. & Systems 2024-03-05 Goeric Huybrechts , Srikanth Ronanki , Xilai Li , Hadis Nosrati , Sravan Bodapati , Katrin Kirchhoff

Transformers have revolutionized machine learning across diverse domains, yet understanding their behavior remains crucial, particularly in high-stakes applications. This paper introduces the contextual counting task, a novel toy problem…

This work is an improved system that we submitted to task 1 of DCASE2023 challenge. We propose a method of low-complexity acoustic scene classification by a parallel attention-convolution network which consists of four modules, including…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-13 Yanxiong Li , Jiaxin Tan , Guoqing Chen , Jialong Li , Yongjie Si , Qianhua He

This work builds together two popular blocks of neural architecture, namely convolutional layers and Transformers, for large language models (LLMs). Non-causal conformers are used ubiquitously in automatic speech recognition. This work aims…

Computation and Language · Computer Science 2023-07-04 Prateek Verma

Face attribute evaluation plays an important role in video surveillance and face analysis. Although methods based on convolution neural networks have made great progress, they inevitably only deal with one local neighborhood with…

Computer Vision and Pattern Recognition · Computer Science 2022-07-13 Decheng Liu , Weijie He , Chunlei Peng , Nannan Wang , Jie Li , Xinbo Gao

Transformers predict over a representation of a sequence. The same data can be written as bytes, characters, or subword tokens, and these representations may be lossless. Yet, under a fixed context window, they need not expose the same…

Machine Learning · Computer Science 2026-05-14 Amirmehdi Jafari Fesharaki , Mohammadamin Rami , Aslan Tchamkerten

The streaming automatic speech recognition (ASR) models are more popular and suitable for voice-based applications. However, non-streaming models provide better performance as they look at the entire audio context. To leverage the benefits…

Sound · Computer Science 2022-08-26 Raviraj Joshi , Subodh Kumar

RNN-Transducers (RNN-Ts) have gained widespread acceptance as an end-to-end model for speech to text conversion because of their high accuracy and streaming capabilities. A typical RNN-T independently encodes the input audio and the text…

Computation and Language · Computer Science 2023-07-12 Vinit S. Unni , Ashish Mittal , Preethi Jyothi , Sunita Sarawagi

Transformer-based speech enhancement models yield impressive results. However, their heterogeneous and complex structure restricts model compression potential, resulting in greater complexity and reduced hardware efficiency. Additionally,…

Hardware Architecture · Computer Science 2025-03-28 Ci-Hao Wu , Tian-Sheuan Chang

We present a transformer-based sarcasm detection model that accounts for the context from the entire conversation thread for more robust predictions. Our model uses deep transformer layers to perform multi-head attentions among the target…

Computation and Language · Computer Science 2020-05-26 Xiangjue Dong , Changmao Li , Jinho D. Choi

Non-hierarchical sparse attention Transformer-based models, such as Longformer and Big Bird, are popular approaches to working with long documents. There are clear benefits to these approaches compared to the original Transformer in terms…

Computation and Language · Computer Science 2022-10-12 Ilias Chalkidis , Xiang Dai , Manos Fergadiotis , Prodromos Malakasiotis , Desmond Elliott

We present a training scheme for streaming automatic speech recognition (ASR) based on recurrent neural network transducers (RNN-T) which allows the encoder network to learn to exploit context audio from a stream, using segmented or…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-16 Andreas Schwarz , Ilya Sklyar , Simon Wiesler

The Transformer-based models with the multi-head self-attention mechanism are widely used in natural language processing, and provide state-of-the-art results. While the pre-trained language backbones are shown to implicitly capture certain…

Computation and Language · Computer Science 2023-12-18 Zhengyuan Liu , Nancy F. Chen

Transformer has become ubiquitous in the deep learning field. One of the key ingredients that destined its success is the self-attention mechanism, which allows fully-connected contextual encoding over input tokens. However, despite its…

Computation and Language · Computer Science 2021-06-08 Shuohang Wang , Luowei Zhou , Zhe Gan , Yen-Chun Chen , Yuwei Fang , Siqi Sun , Yu Cheng , Jingjing Liu