English
Related papers

Related papers: FSR: Accelerating the Inference Process of Transdu…

200 papers

Self-supervised learning has been actively studied in time series domain recently, especially for masked reconstruction. Most of these methods follow the "Pre-training + Fine-tuning" paradigm in which a new decoder replaces the pre-trained…

Machine Learning · Computer Science 2023-11-08 Hao Liu , Jinrui Gan , Xiaoxuan Fan , Yi Zhang , Chuanxian Luo , Jing Zhang , Guangxin Jiang , Yucheng Qian , Changwei Zhao , Huan Ma , Zhenyu Guo

Speaker-role diarization (RD), such as doctor vs. patient or lawyer vs. client, is practically often more useful than conventional speaker diarization (SD), which assigns only generic labels (speaker-1, speaker-2). The state-of-the-art…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-23 Arindam Ghosh , Mark Fuhs , Bongjun Kim , Anurag Chowdhury , Monika Woszczyna

Structured prediction models aim at solving a type of problem where the output is a complex structure, rather than a single variable. Performing knowledge distillation for such models is not trivial due to their exponentially large output…

Machine Learning · Computer Science 2022-03-10 Wenye Lin , Yangming Li , Lemao Liu , Shuming Shi , Hai-tao Zheng

Transformers have become a predominant machine learning workload, they are not only the de-facto standard for natural language processing tasks, but they are also being deployed in other domains such as vision and speech recognition. Many…

Machine Learning · Computer Science 2022-06-23 Ibrahim Ahmed , Sahil Parmar , Matthew Boyd , Michael Beidler , Kris Kang , Bill Liu , Kyle Roach , John Kim , Dennis Abts

Recent advances in speech-aware language models have coupled strong acoustic encoders with large language models, enabling systems that move beyond transcription to produce richer outputs. Among these, word-level timestamp prediction is…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-28 Xulin Fan , Vishal Sunder , Samuel Thomas , Mark Hasegawa-Johnson , Brian Kingsbury , George Saon

Transfer learning can address the learning tasks of unlabeled data in the target domain by leveraging plenty of labeled data from a different but related source domain. A core issue in transfer learning is to learn a shared feature space in…

Machine Learning · Computer Science 2019-01-10 Peng Xu , Zhaohong Deng , Jun Wang , Qun Zhang , Shitong Wang

In this paper, we propose to improve end-to-end (E2E) spoken language understand (SLU) in an RNN transducer model (RNN-T) by incorporating a joint self-conditioned CTC automatic speech recognition (ASR) objective. Our proposed model is akin…

Machine Learning · Computer Science 2025-01-06 Vishal Sunder , Eric Fosler-Lussier

As a robust and large-scale multilingual speech recognition model, Whisper has demonstrated impressive results in many low-resource and out-of-distribution scenarios. However, its encoder-decoder structure hinders its application to…

Sound · Computer Science 2025-05-06 Haoyu Wang , Guoqiang Hu , Guodong Lin , Wei-Qiang Zhang , Jian Li

End-to-end (E2E) models have gained attention in the research field of automatic speech recognition (ASR). Many E2E models proposed so far assume left-to-right autoregressive generation of an output token sequence except for connectionist…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-17 Yuya Fujita , Shinji Watanabe , Motoi Omachi , Xuankai Chan

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing…

Recently, Transformer-based encoder-decoder models have demonstrated strong performance in multilingual speech recognition. However, the decoder's autoregressive nature and large size introduce significant bottlenecks during inference.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-28 Yunkyu Lim , Jihwan Park , Hyung Yong Kim , Hanbin Lee , Byeong-Yeol Kim

In this work we propose a novel token-based training strategy that improves Transformer-Transducer (T-T) based speaker change detection (SCD) performance. The conventional T-T based SCD model loss optimizes all output tokens equally. Due to…

Audio and Speech Processing · Electrical Eng. & Systems 2022-12-06 Guanlong Zhao , Quan Wang , Han Lu , Yiling Huang , Ignacio Lopez Moreno

With the success of language pretraining, it is highly desirable to develop more efficient architectures of good scalability that can exploit the abundant unlabeled data at a lower cost. To improve the efficiency, we examine the…

Machine Learning · Computer Science 2020-06-08 Zihang Dai , Guokun Lai , Yiming Yang , Quoc V. Le

Understanding visual scenes relies more and more on dense pixel-wise classification obtained via deep fully convolutional neural networks. However, due to the nature of the networks, predictions often suffer from blurry boundaries and…

Neural and Evolutionary Computing · Computer Science 2019-09-05 Nicolas Audebert , Alexandre Boulch , Bertrand Le Saux , Sébastien Lefèvre

The Transformer is a highly successful deep learning model that has revolutionised the world of artificial neural networks, first in natural language processing and later in computer vision. This model is based on the attention mechanism…

Machine Learning · Computer Science 2023-05-09 Riccardo Ughi , Eugenio Lomurno , Matteo Matteucci

End-to-end speech recognition is a promising technology for enabling compact automatic speech recognition (ASR) systems since it can unify the acoustic and language model into a single neural network. However, as a drawback, training of…

Computation and Language · Computer Science 2022-02-17 Yotaro Kubo , Shigeki Karita , Michiel Bacchiani

Scarcity of labeled data has motivated the development of semi-supervised learning methods, which learn from large portions of unlabeled data alongside a few labeled samples. Consistency Regularization between model's predictions under…

Computer Vision and Pattern Recognition · Computer Science 2020-07-16 Aamir Mustafa , Rafal K. Mantiuk

Recently very deep transformers have outperformed conventional bi-directional long short-term memory networks by a large margin in speech recognition. However, to put it into production usage, inference computation cost is still a serious…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-27 Nanxin Chen , Shinji Watanabe , Jesús Villalba , Najim Dehak

Incorporating computational fluid dynamics in the design process of jets, spacecraft, or gas turbine engines is often challenged by the required computational resources and simulation time, which depend on the chosen physics-based…

Computational Physics · Physics 2019-12-09 Cristina White , Daniela Ushizima , Charbel Farhat

This paper presents a transfer learning method in speech emotion recognition based on a Time-Delay Neural Network (TDNN) architecture. A major challenge in the current speech-based emotion detection research is data scarcity. The proposed…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-18 Sitong Zhou , Homayoon Beigi
‹ Prev 1 8 9 10 Next ›