English
Related papers

Related papers: Feature learning for efficient ASR-free keyword sp…

200 papers

This study tackles unsupervised subword modeling in the zero-resource scenario, learning frame-level speech representation that is phonetically discriminative and speaker-invariant, using only untranscribed speech for target languages.…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-29 Siyuan Feng , Tan Lee

This study addresses the problem of unsupervised subword unit discovery from untranscribed speech. It forms the basis of the ultimate goal of ZeroSpeech 2019, building text-to-speech systems without text labels. In this work, unit discovery…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-29 Siyuan Feng , Tan Lee , Zhiyuan Peng

There are a number of studies about extraction of bottleneck (BN) features from deep neural networks (DNNs)trained to discriminate speakers, pass-phrases and triphone states for improving the performance of text-dependent speaker…

Sound · Computer Science 2019-05-14 Achintya kr. Sarkar , Zheng-Hua Tan , Hao Tang , Suwon Shon , James Glass

Keyword spotting (KWS) has become an indispensable part of many intelligent devices surrounding us, as audio is one of the most efficient ways of interacting with these devices. The accuracy and performance of KWS solutions have been the…

Sound · Computer Science 2021-11-10 Mehmet Gorkem Ulkar , Osman Erman Okman

Deep neural networks provide effective solutions to small-footprint keyword spotting (KWS). However, if training data is limited, it remains challenging to achieve robust and highly accurate KWS in real-world scenarios where unseen sounds…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-14 Menglong Xu , Shengqiang Li , Chengdong Liang , Xiao-Lei Zhang

Developing a practical speech recognizer for a low resource language is challenging, not only because of the (potentially unknown) properties of the language, but also because test data may not be from the same domain as the available…

Computation and Language · Computer Science 2018-10-02 Siddharth Dalmia , Xinjian Li , Florian Metze , Alan W. Black

Keyword Spotting (KWS) enables speech-based user interaction on smart devices. Always-on and battery-powered application scenarios for smart devices put constraints on hardware resources and power consumption, while also demanding high…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-05 Simon Mittermaier , Ludwig Kürzinger , Bernd Waschneck , Gerhard Rigoll

Word spotting has become a field of strong research interest in document image analysis over the last years. Recently, AttributeSVMs were proposed which predict a binary attribute representation. At their time, this influential method…

Computer Vision and Pattern Recognition · Computer Science 2017-12-21 Sebastian Sudholt , Gernot Fink

Speech enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality. Conventional time-frequency (TF) domain methods focus on predicting TF-masks or speech spectrum, via a naive convolution…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-24 Yanxin Hu , Yun Liu , Shubo Lv , Mengtao Xing , Shimin Zhang , Yihui Fu , Jian Wu , Bihong Zhang , Lei Xie

Keyword spotting is an important research field because it plays a key role in device wake-up and user interaction on smart devices. However, it is challenging to minimize errors while operating efficiently in devices with limited resources…

Sound · Computer Science 2023-07-06 Byeonggeun Kim , Simyung Chang , Jinkyu Lee , Dooyong Sung

In this paper, we aim to improve the robustness of Keyword Spotting (KWS) systems in noisy environments while keeping a small memory footprint. We propose a new convolutional neural network (CNN) called FCA-Net, which combines mixer…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-30 Yuanxi Lin , Yuriy Evgenyevich Gapanyuk

Acoustic word embeddings (AWEs) are fixed-dimensional representations of variable-length speech segments. For zero-resource languages where labelled data is not available, one AWE approach is to use unsupervised autoencoder-based recurrent…

Computation and Language · Computer Science 2021-03-22 Christiaan Jacobs , Yevgen Matusevych , Herman Kamper

Furui first demonstrated that the identity of both consonant and vowel can be perceived from the C-V transition; later, Stevens proposed that acoustic landmarks are the primary cues for speech perception, and that steady-state regions are…

Computation and Language · Computer Science 2018-05-16 Di He , Boon Pang Lim , Xuesong Yang , Mark Hasegawa-Johnson , Deming Chen

Open vocabulary keyword spotting is a crucial and challenging task in automatic speech recognition (ASR) that focuses on detecting user-defined keywords within a spoken utterance. Keyword spotting methods commonly map the audio utterance…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-18 Aviv Navon , Aviv Shamsian , Neta Glazer , Gill Hetz , Joseph Keshet

Attention mechanisms, such as local and non-local attention, play a fundamental role in recent deep learning based speech enhancement (SE) systems. However, natural speech contains many fast-changing and relatively brief acoustic events,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-01-16 Xinmeng Xu , Weiping Tu , Yuhong Yang

Non-parallel data voice conversion (VC) have achieved considerable breakthroughs recently through introducing bottleneck features (BNFs) extracted by the automatic speech recognition(ASR) model. However, selection of BNFs have a significant…

Sound · Computer Science 2022-03-25 Xintao Zhao , Feng Liu , Changhe Song , Zhiyong Wu , Shiyin Kang , Deyi Tuo , Helen Meng

The success of retrieval-augmented language models in various natural language processing (NLP) tasks has been constrained in automatic speech recognition (ASR) applications due to challenges in constructing fine-grained audio-text…

Sound · Computer Science 2024-02-06 Jiaming Zhou , Shiwan Zhao , Yaqi Liu , Wenjia Zeng , Yong Chen , Yong Qin

Learning algorithms for natural language processing (NLP) tasks traditionally rely on manually defined relevant contextual features. On the other hand, neural network models using an only distributional representation of words have been…

Computation and Language · Computer Science 2017-11-30 Kushal Chawla , Sunil Kumar Sahu , Ashish Anand

In settings where only unlabelled speech data is available, zero-resource speech technology needs to be developed without transcriptions, pronunciation dictionaries, or language modelling text. There are two central problems in…

Computation and Language · Computer Science 2017-01-05 Herman Kamper

The performance of automatic speech recognition (ASR) has improved tremendously due to the application of deep neural networks (DNNs). Despite this progress, building a new ASR system remains a challenging task, requiring various resources,…

Computation and Language · Computer Science 2015-10-20 Yajie Miao , Mohammad Gowayyed , Florian Metze