English
Related papers

Related papers: An Asynchronous WFST-Based Decoder For Automatic S…

200 papers

Using a vision-inspired keyword spotting framework, we propose an architecture with input-dependent dynamic depth capable of processing streaming audio. Specifically, we extend a conformer encoder with trainable binary gates that allow us…

Sound · Computer Science 2024-04-02 Alexandre Bittar , Paul Dixon , Mohammad Samragh , Kumari Nishu , Devang Naik

We present an optimized weighted finite-state transducer (WFST) decoder capable of online streaming and offline batch processing of audio using Graphics Processing Units (GPUs). The decoder is efficient in memory utilization, input/output…

Computation and Language · Computer Science 2020-02-17 Hugo Braun , Justin Luitjens , Ryan Leary , Tim Kaldewey , Daniel Povey

We propose a constraint-based flow-sensitive static analysis for concurrent programs by iteratively composing thread-modular abstract interpreters via the use of a system of lightweight constraints. Our method is compositional in that it…

Programming Languages · Computer Science 2017-10-02 Markus Kusano , Chao Wang

Unseen noise signal which is not considered in a model training process is difficult to anticipate and would lead to performance degradation. Various methods have been investigated to mitigate unseen noise. In our previous work, an…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-24 Donghyeon Kim , Gwantae Kim , Bokyeung Lee , Jeong-gi Kwak , David K. Han , Hanseok Ko

While Diffusion Generative Models have achieved great success on image generation tasks, how to efficiently and effectively incorporate them into speech generation especially translation tasks remains a non-trivial problem. Specifically,…

Computation and Language · Computer Science 2023-10-27 Yongxin Zhu , Zhujin Gao , Xinyuan Zhou , Zhongyi Ye , Linli Xu

Dynamical sampling deals with signals that evolve in time under the action of a linear operator. The purpose of the present paper is to analyze the performance of the basic dynamical sampling algorithms in the finite dimensional case and…

Numerical Analysis · Mathematics 2018-10-16 Akram Aldroubi , Longxiu Huang , Ilya Krishtal , Akos Ledeczi , Roy R. Lederman , Peter Volgyesi

Unsupervised representation learning, particularly sequential disentanglement, aims to separate static and dynamic factors of variation in data without relying on labels. This remains a challenging problem, as existing approaches based on…

Machine Learning · Computer Science 2025-10-08 Hedi Zisling , Ilan Naiman , Nimrod Berman , Supasorn Suwajanakorn , Omri Azencot

Audio-driven talking-head generation has advanced rapidly with diffusion-based generative models, yet producing temporally coherent videos with fine-grained motion control remains challenging. We propose DEMO, a flow-matching generative…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Peiyin Chen , Zhuowei Yang , Hui Feng , Sheng Jiang , Rui Yan

In this paper, we focus on Whisper, a recent automatic speech recognition model trained with a massive 680k hour labeled speech corpus recorded in diverse conditions. We first show an interesting finding that while Whisper is very robust…

Sound · Computer Science 2023-10-10 Yuan Gong , Sameer Khurana , Leonid Karlinsky , James Glass

Deciphering natural language from brain activity through non-invasive devices remains a formidable challenge. Previous non-invasive decoders either require multiple experiments with identical stimuli to pinpoint cortical regions and enhance…

Computation and Language · Computer Science 2024-03-20 Cenyuan Zhang , Xiaoqing Zheng , Ruicheng Yin , Shujie Geng , Jianhan Xu , Xuan Gao , Changze Lv , Zixuan Ling , Xuanjing Huang , Miao Cao , Jianfeng Feng

Attention-based encoder-decoder (AED) models have shown impressive performance in ASR. However, most existing AED methods neglect to simultaneously leverage both acoustic and semantic features in decoder, which is crucial for generating…

Computation and Language · Computer Science 2023-05-24 Tian-Hao Zhang , Hai-Bo Qin , Zhi-Hao Lai , Song-Lu Chen , Qi Liu , Feng Chen , Xinyuan Qian , Xu-Cheng Yin

In this paper, we propose an efficient and accurate streaming speech recognition model based on the FastConformer architecture. We adapted the FastConformer architecture for streaming applications through: (1) constraining both the…

Computation and Language · Computer Science 2024-05-06 Vahid Noroozi , Somshubra Majumdar , Ankur Kumar , Jagadeesh Balam , Boris Ginsburg

Discrete diffusion language models have shown strong potential for text generation, yet standard supervised fine-tuning (SFT) misaligns with their semi-autoregressive inference: training randomly masks tokens across the entire response,…

Computation and Language · Computer Science 2025-10-24 Bowen Sun , Yujun Cai , Ming-Hsuan Yang , Yiwei Wang

Contextual biasing (CB) improves automatic speech recognition for rare and unseen phrases. Recent studies have introduced dynamic vocabulary, which represents context phrases as expandable tokens in autoregressive (AR) models. This method…

Computation and Language · Computer Science 2025-06-04 Yui Sudo , Yosuke Fukumoto , Muhammad Shakeel , Yifan Peng , Chyi-Jiunn Lin , Shinji Watanabe

We introduce DiffuseST, a low-latency, direct speech-to-speech translation system capable of preserving the input speaker's voice zero-shot while translating from multiple source languages into English. We experiment with the synthesizer…

We propose a two-stream convolutional network for audio recognition, that operates on time-frequency spectrogram inputs. Following similar success in visual recognition, we learn Slow-Fast auditory streams with separable convolutions and…

Sound · Computer Science 2021-03-08 Evangelos Kazakos , Arsha Nagrani , Andrew Zisserman , Dima Damen

2D convolution is widely used in sound event detection (SED) to recognize two dimensional time-frequency patterns of sound events. However, 2D convolution enforces translation equivariance on sound events along both time and frequency axis…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-05 Hyeonuk Nam , Seong-Hu Kim , Byeong-Yun Ko , Yong-Hwa Park

Brain-inspired hyperdimensional computing (HDC) has been recently considered a promising learning approach for resource-constrained devices. However, existing approaches use static encoders that are never updated during the learning…

Machine Learning · Computer Science 2023-04-13 Junyao Wang , Sitao Huang , Mohsen Imani

The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…

Sound · Computer Science 2018-11-07 Santiago Pascual , Antonio Bonafonte , Joan Serrà

Recent top-performing temporal 3D detectors based on Lidars have increasingly adopted region-based paradigms. They first generate coarse proposals, followed by encoding and fusing regional features. However, indiscriminate sampling and…

Computer Vision and Pattern Recognition · Computer Science 2025-03-05 Chenxu Dang , Zaipeng Duan , Pei An , Xinmin Zhang , Xuzhong Hu , Jie Ma