English
Related papers

Related papers: E-Branchformer: Branchformer with Enhanced merging…

200 papers

End-to-end speech recognition generally uses hand-engineered acoustic features as input and excludes the feature extraction module from its joint optimization. To extract learnable and adaptive features and mitigate information loss, we…

Sound · Computer Science 2021-06-09 Max W. Y. Lam , Jun Wang , Chao Weng , Dan Su , Dong Yu

Acoustic Echo Cancellation (AEC) is essential for accurate recognition of queries spoken to a smart speaker that is playing out audio. Previous work has shown that a neural AEC model operating on log-mel spectral features (denoted "logmel"…

Audio and Speech Processing · Electrical Eng. & Systems 2022-05-10 Sankaran Panchapagesan , Arun Narayanan , Turaj Zakizadeh Shabestary , Shuai Shao , Nathan Howard , Alex Park , James Walker , Alexander Gruenstein

While integrating speech encoder with LLM requires substantial data and resources, use cases face limitations due to insufficient availability. To address this, we propose a solution with a parameter-efficient adapter that converts speech…

Computation and Language · Computer Science 2025-09-08 Jaekwon Yoo , Kunal Chandiramani , Divya Tadimeti , Abenezer Girma , Chandra Dhir

Recently, conformer-based end-to-end automatic speech recognition, which outperforms recurrent neural network based ones, has received much attention. Although the parallel computing of conformer is more efficient than recurrent neural…

Sound · Computer Science 2021-07-26 Shengqiang Li , Menglong Xu , Xiao-Lei Zhang

Brain tumor segmentation is an active research area due to the difficulty in delineating highly complex shaped and textured tumors as well as the failure of the commonly used U-Net architectures. The combination of different neural…

Image and Video Processing · Electrical Eng. & Systems 2023-08-02 Lanhong Yao , Zheyuan Zhang , Ulas Bagci

Visual recognition of speech using the lip movement is called Lip-reading. Recent developments in this nascent field uses different neural networks as feature extractors which serve as input to a model which can map the temporal…

Computer Vision and Pattern Recognition · Computer Science 2018-06-01 Dharin Parekh , Ankitesh Gupta , Shharrnam Chhatpar , Anmol Yash Kumar , Manasi Kulkarni

Transformers have shown dominant performance across a range of domains including language and vision. However, their computational cost grows quadratically with the sequence length, making their usage prohibitive for resource-constrained…

Computation and Language · Computer Science 2023-10-24 Yinghan Long , Sayeed Shafayet Chowdhury , Kaushik Roy

Source separation can improve automatic speech recognition (ASR) under multi-party meeting scenarios by extracting single-speaker signals from overlapped speech. Despite the success of self-supervised learning models in single-channel…

Audio and Speech Processing · Electrical Eng. & Systems 2023-04-04 Yuang Li , Xianrui Zheng , Philip C. Woodland

Automatic speech recognition (ASR) has reached a level of accuracy in recent years, that even outperforms humans in transcribing speech to text. Nevertheless, all current ASR approaches show a certain weakness against ambient noise. To…

Sound · Computer Science 2023-12-22 Christopher Simic , Tobias Bocklet

Conformer has shown a great success in automatic speech recognition (ASR) on many public benchmarks. One of its crucial drawbacks is the quadratic time-space complexity with respect to the input sequence length, which prohibits the model to…

Sound · Computer Science 2022-03-30 Jingyu Sun , Guiping Zhong , Dinghao Zhou , Baoxiang Li , Yiran Zhong

End-to-end modeling (E2E) of automatic speech recognition (ASR) blends all the components of a traditional speech recognition system into a unified model. Although it simplifies training and decoding pipelines, the unified model is hard to…

Computation and Language · Computer Science 2018-12-06 Zhehuai Chen , Mahaveer Jain , Yongqiang Wang , Michael L. Seltzer , Christian Fuegen

Temporal convolutions have been the paradigm of choice in action segmentation, which enhances long-term receptive fields by increasing convolution layers. However, high layers cause the loss of local information necessary for frame…

Computer Vision and Pattern Recognition · Computer Science 2022-05-20 Jiahui Wang , Zhenyou Wang , Shanna Zhuang , Hui Wang

End-to-end models with large capacity have significantly improved multilingual automatic speech recognition, but their computation cost poses challenges for on-device applications. We propose a streaming truly multilingual Conformer…

Computation and Language · Computer Science 2023-05-26 Ke Hu , Bo Li , Tara N. Sainath , Yu Zhang , Francoise Beaufays

We propose a cross-modal transformer-based neural correction models that refines the output of an automatic speech recognition (ASR) system so as to exclude ASR errors. Generally, neural correction models are composed of encoder-decoder…

Computation and Language · Computer Science 2021-07-06 Tomohiro Tanaka , Ryo Masumura , Mana Ihori , Akihiko Takashima , Takafumi Moriya , Takanori Ashihara , Shota Orihashi , Naoki Makishima

Transformer models have demonstrated remarkable success in many domains such as natural language processing (NLP) and computer vision. With the growing interest in transformer-based architectures, they are now utilized for gesture…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Mallika Garg , Debashis Ghosh , Pyari Mohan Pradhan

Recently, attention-based encoder-decoder (AED) models have shown high performance for end-to-end automatic speech recognition (ASR) across several tasks. Addressing overconfidence in such models, in this paper we introduce the concept of…

Audio and Speech Processing · Electrical Eng. & Systems 2021-12-16 Timo Lohrenz , Patrick Schwarz , Zhengyang Li , Tim Fingscheidt

Transformers have recently achieved state-of-the-art performance in speech separation. These models, however, are computationally demanding and require a lot of learnable parameters. This paper explores Transformer-based speech separation…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-17 Luca Della Libera , Cem Subakan , Mirco Ravanelli , Samuele Cornell , Frédéric Lepoutre , François Grondin

End-to-end models are fast replacing the conventional hybrid models in automatic speech recognition. Transformer, a sequence-to-sequence model, based on self-attention popularly used in machine translation tasks, has given promising results…

Audio and Speech Processing · Electrical Eng. & Systems 2021-11-19 Vishwas M. Shetty , Metilda Sagaya Mary N J , S. Umesh

Traditional automatic speech recognition~(ASR) systems usually focus on individual utterances, without considering long-form speech with useful historical information, which is more practical in real scenarios. Simply attending longer…

Sound · Computer Science 2022-11-18 Xun Gong , Yu Wu , Jinyu Li , Shujie Liu , Rui Zhao , Xie Chen , Yanmin Qian

Self-supervised learning (SSL) is a powerful technique for learning representations from unlabeled data. Transformer based models such as HuBERT, which consist a feature extractor and transformer layers, are leading the field in the speech…

Audio and Speech Processing · Electrical Eng. & Systems 2023-01-23 Zih-Ching Chen , Yu-Shun Sung , Hung-yi Lee