English
Related papers

Related papers: Layer Reduction: Accelerating Conformer-Based Self…

200 papers

With the rise and ubiquity of larger deep learning models, the need for high-quality compression techniques is growing in order to deploy these models widely. The sheer parameter count of these models makes it difficult to fit them into the…

Computation and Language · Computer Science 2025-04-01 Neha Verma , Kenton Murray , Kevin Duh

Recently, Transformer-based architectures have been explored for speaker embedding extraction. Although the Transformer employs the self-attention mechanism to efficiently model the global interaction between token embeddings, it is…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-02 Mufan Sang , Yong Zhao , Gang Liu , John H. L. Hansen , Jian Wu

Parameter-efficient transfer learning (PETL) aims to adapt large pre-trained models using limited parameters. While most PETL approaches update the added parameters and freeze pre-trained weights during training, the minimal impact of…

Computer Vision and Pattern Recognition · Computer Science 2024-07-22 Ruizi Han , Jinglei Tang

Transformer has shown promising results in many sequence to sequence transformation tasks recently. It utilizes a number of feed-forward self-attention layers to replace the recurrent neural networks (RNN) in attention-based encoder decoder…

Computation and Language · Computer Science 2020-12-01 Pan Zhou , Ruchao Fan , Wei Chen , Jia Jia

With the proliferation of mobile devices and the Internet of Things, deep learning models are increasingly deployed on devices with limited computing resources and memory, and are exposed to the threat of adversarial noise. Learning deep…

Computer Vision and Pattern Recognition · Computer Science 2021-12-30 Xian Wei , Yanhui Huang , Yangyu Xu , Mingsong Chen , Hai Lan , Yuanxiang Li , Zhongfeng Wang , Xuan Tang

The Conformer model is an excellent architecture for speech recognition modeling that effectively utilizes the hybrid losses of connectionist temporal classification (CTC) and attention to train model parameters. To improve the decoding…

Sound · Computer Science 2022-04-11 Nick J. C. Wang , Zongfeng Quan , Shaojun Wang , Jing Xiao

Initially introduced as a machine translation model, the Transformer architecture has now become the foundation for modern deep learning architecture, with applications in a wide range of fields, from computer vision to natural language…

Computation and Language · Computer Science 2024-06-21 Martin Courtois , Malte Ostendorff , Leonhard Hennig , Georg Rehm

Sentence-level representations are necessary for various NLP tasks. Recurrent neural networks have proven to be very effective in learning distributed representations and can be trained efficiently on natural language inference tasks. We…

Computation and Language · Computer Science 2019-08-15 Aarne Talman , Anssi Yli-Jyrä , Jörg Tiedemann

The large attention-based encoder-decoder network (Transformer) has become prevailing recently due to its effectiveness. But the high computation complexity of its decoder raises the inefficiency issue. By examining the mathematic…

Computation and Language · Computer Science 2023-05-12 Yanyang Li , Ye Lin , Tong Xiao , Jingbo Zhu

The recent emergence of joint CTC-Attention model shows significant improvement in automatic speech recognition (ASR). The improvement largely lies in the modeling of linguistic information by decoder. The decoder joint-optimized with an…

Computation and Language · Computer Science 2022-10-27 Xulong Zhang , Jianzong Wang , Ning Cheng , Mengyuan Zhao , Zhiyong Zhang , Jing Xiao

The workflow of pretraining and fine-tuning has emerged as a popular paradigm for solving various NLP and V&L (Vision-and-Language) downstream tasks. With the capacity of pretrained models growing rapidly, how to perform parameter-efficient…

Computation and Language · Computer Science 2022-03-09 Zhengkun Zhang , Wenya Guo , Xiaojun Meng , Yasheng Wang , Yadao Wang , Xin Jiang , Qun Liu , Zhenglu Yang

End-to-end spoken language understanding (SLU) systems benefit from pretraining on large corpora, followed by fine-tuning on application-specific data. The resulting models are too large for on-edge applications. For instance, BERT-based…

Computation and Language · Computer Science 2022-06-30 Pu Wang , Hugo Van hamme

Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other…

Computation and Language · Computer Science 2023-05-17 Nurullah Sevim , Ege Ozan Özyedek , Furkan Şahinuç , Aykut Koç

Compressing self-supervised models has become increasingly necessary, as self-supervised models become larger. While previous approaches have primarily focused on compressing the model size, shortening sequences is also effective in…

Computation and Language · Computer Science 2022-10-26 Yen Meng , Hsuan-Jui Chen , Jiatong Shi , Shinji Watanabe , Paola Garcia , Hung-yi Lee , Hao Tang

Large transformer-based language models dominate modern NLP, yet our understanding of how they encode linguistic information relies primarily on studies of early models like BERT and GPT-2. We systematically probe 25 models from BERT Base…

Computation and Language · Computer Science 2026-04-23 Michael Li , Nishant Subramani

This paper presents a method to accelerate the inference process of diffusion transformer (DiT)-based text-to-speech (TTS) models by applying a selective caching mechanism to transformer layers. Specifically, I integrate SmoothCache into…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-11 Siratish Sakpiboonchit

Automatic speech quality assessment is essential for audio researchers, developers, speech and language pathologists, and system quality engineers. The current state-of-the-art systems are based on framewise speech features (hand-engineered…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-15 Karl El Hajal , Zihan Wu , Neil Scheidwasser-Clow , Gasser Elbanna , Milos Cernak

Transfer learning techniques aim to leverage information from multiple related datasets to enhance prediction quality against a target dataset. Such methods have been adopted in the context of high-dimensional sparse regression, and some…

Machine Learning · Statistics 2025-01-31 Koki Okajima , Tomoyuki Obuchi

Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forces them to absorb task-specific information, which can result in catastrophic forgetting and loss of…

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…