English
Related papers

Related papers: Multi-Stream Transformers

200 papers

Transformer-based models have achieved state-of-the-art performance on speech translation tasks. However, the model architecture is not efficient enough for streaming scenarios since self-attention is computed over an entire input sequence…

Computation and Language · Computer Science 2020-11-03 Xutai Ma , Yongqiang Wang , Mohammad Javad Dousti , Philipp Koehn , Juan Pino

Transformer-based models have dramatically increased their size and parameter count to tackle increasingly complex tasks. At the same time, there is a growing demand for high performance, low-latency inference on devices with limited…

Machine Learning · Computer Science 2026-04-01 Ginés Carreto Picón , Peng Yuan Zhou , Qi Zhang , Alexandros Iosifidis

The advent of Transformer-based models has surpassed the barriers of text. When working with speech, we must face a problem: the sequence length of an audio input is not suitable for the Transformer. To bypass this problem, a usual approach…

Computation and Language · Computer Science 2021-07-08 Belen Alastruey , Gerard I. Gállego , Marta R. Costa-jussà

Previous multi-task dense prediction studies developed complex pipelines such as multi-modal distillations in multiple stages or searching for task relational contexts for each task. The core insight beyond these methods is to maximize the…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Yangyang Xu , Xiangtai Li , Haobo Yuan , Yibo Yang , Lefei Zhang

In this paper we present an end-to-end speech recognition model with Transformer encoders that can be used in a streaming speech recognition system. Transformer computation blocks based on self-attention are used to encode both audio and…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-18 Qian Zhang , Han Lu , Hasim Sak , Anshuman Tripathi , Erik McDermott , Stephen Koo , Shankar Kumar

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

Transformer-based models have been achieving state-of-the-art results in several fields of Natural Language Processing. However, its direct application to speech tasks is not trivial. The nature of this sequences carries problems such as…

Computation and Language · Computer Science 2022-05-17 Gerard Sant , Gerard I. Gállego , Belen Alastruey , Marta R. Costa-Jussà

Although the Transformer is currently the best-performing architecture in the homogeneous configuration (self-attention only) in Neural Machine Translation, many State-of-the-Art models in Natural Language Processing are made of a…

Computation and Language · Computer Science 2024-01-02 Jia Cheng Hu , Roberto Cavicchioli , Giulia Berardinelli , Alessandro Capotondi

In this paper, we propose a novel architecture for multi-modal speech and text input. We combine pretrained speech and text encoders using multi-headed cross-modal attention and jointly fine-tune on the target problem. The resultant…

Computation and Language · Computer Science 2022-04-21 Karan Singla , Daniel Pressel , Ryan Price , Bhargav Srinivas Chinnari , Yeon-Jun Kim , Srinivas Bangalore

Representation learning is important for solving sequence-to-sequence problems in natural language processing. Representation learning transforms raw data into vector-form representations while preserving their features. However, data with…

Computation and Language · Computer Science 2023-01-12 Yunhao Yang , Zhaokun Xue , Andrew Whinston

In clinical scenarios, multi-specialist consultation could significantly benefit the diagnosis, especially for intricate cases. This inspires us to explore a "multi-expert joint diagnosis" mechanism to upgrade the existing "single expert"…

Computer Vision and Pattern Recognition · Computer Science 2023-04-06 Zhanyu Wang , Lingqiao Liu , Lei Wang , Luping Zhou

Pretrained molecular encoders have become indispensable in computational chemistry for tasks such as property prediction and molecular generation. However, the standard practice of relying solely on final-layer embeddings for downstream…

Machine Learning · Computer Science 2025-10-16 Luis Pinto

We introduce Transfusion, a recipe for training a multi-modal model over discrete and continuous data. Transfusion combines the language modeling loss function (next token prediction) with diffusion to train a single transformer over…

Artificial Intelligence · Computer Science 2024-08-21 Chunting Zhou , Lili Yu , Arun Babu , Kushal Tirumala , Michihiro Yasunaga , Leonid Shamis , Jacob Kahn , Xuezhe Ma , Luke Zettlemoyer , Omer Levy

Recently, fully recurrent neural network (RNN) based end-to-end models have been proven to be effective for multi-speaker speech recognition in both the single-channel and multi-channel scenarios. In this work, we explore the use of…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-14 Xuankai Chang , Wangyou Zhang , Yanmin Qian , Jonathan Le Roux , Shinji Watanabe

Understanding how information propagates through Transformer models is a key challenge for interpretability. In this work, we study the effects of minimal token perturbations on the embedding space. In our experiments, we analyze the…

Machine Learning · Computer Science 2025-06-24 Eddie Conti , Alejandro Astruc , Alvaro Parafita , Axel Brando

This paper proposes a novel two-stream encoder-decoder network, which utilizes both the high-level and the low-level image features for precisely localizing forged regions in a manipulated image. This is motivated from the fact that the…

Computer Vision and Pattern Recognition · Computer Science 2020-09-29 Aniruddha Mazumdar , Prabin Kumar Bora

Decoder-only transformers compute the conditional probability of the next token from a sequence of past observations. This paper derives, from first principles, inference architectures that solve the same prediction problem - and in doing…

Machine Learning · Computer Science 2026-05-18 Aditya Kudre , Heng-Sheng Chang , Prashant G. Mehta

Identifying multiple speakers without knowing where a speaker's voice is in a recording is a challenging task. This paper proposes a hierarchical network with transformer encoders and memory mechanism to address this problem. The proposed…

Sound · Computer Science 2020-11-02 Yanpei Shi , Mingjie Chen , Qiang Huang , Thomas Hain

Transformer architectures, capable of capturing sequential dependencies in the history of user interactions, have become the dominant approach in sequential recommender systems. Despite their success, such models consider sequence elements…

Information Retrieval · Computer Science 2026-03-02 Artur Gimranov , Viacheslav Yusupov , Elfat Sabitov , Tatyana Matveeva , Anton Lysenko , Ruslan Israfilov , Evgeny Frolov

Transformers process tokens in parallel but are temporally shallow: at position $t$, each layer attends to key-value pairs computed based on the previous layer, yielding a depth capped by the number of layers. Recurrent models offer…

Machine Learning · Computer Science 2026-04-24 Costin-Andrei Oncescu , Depen Morwani , Samy Jelassi , Alexandru Meterez , Mujin Kwun , Sham Kakade