English
Related papers

Related papers: Acoustic span embeddings for multilingual query-by…

200 papers

Pre-trained speech representations like wav2vec 2.0 are a powerful tool for automatic speech recognition (ASR). Yet many endangered languages lack sufficient data for pre-training such models, or are predominantly oral vernaculars without a…

Existing deep learning based speech enhancement (SE) methods either use blind end-to-end training or explicitly incorporate speaker embedding or phonetic information into the SE network to enhance speech quality. In this paper, we perceive…

Sound · Computer Science 2023-02-27 Yifei Xin , Xiulian Peng , Yan Lu

End-to-end (E2E) automatic speech recognition (ASR) methods exhibit remarkable performance. However, since the performance of such methods is intrinsically linked to the context present in the training data, E2E-ASR methods do not perform…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-22 Yui Sudo , Muhammad Shakeel , Yosuke Fukumoto , Yifan Peng , Shinji Watanabe

Segmental models are sequence prediction models in which scores of hypotheses are based on entire variable-length segments of frames. We consider segmental models for whole-word ("acoustic-to-word") speech recognition, with the feature…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-25 Bowen Shi , Shane Settle , Karen Livescu

Existing keyword spotting (KWS) systems primarily rely on predefined keyword phrases. However, the ability to recognize customized keywords is crucial for tailoring interactions with intelligent devices. In this paper, we present a novel…

Computation and Language · Computer Science 2024-11-26 Zhenyu Wang , Shuyu Kong , Li Wan , Biqiao Zhang , Yiteng Huang , Mumin Jin , Ming Sun , Xin Lei , Zhaojun Yang

This paper introduces a novel approach for streaming openvocabulary keyword spotting (KWS) with text-based keyword enrollment. For every input frame, the proposed method finds the optimal alignment ending at the frame using connectionist…

Sound · Computer Science 2024-09-27 Sichen Jin , Youngmoon Jung , Seungjin Lee , Jaeyoung Roh , Changwoo Han , Hoonyoung Cho

We propose a new unsupervised model for mapping a variable-duration speech segment to a fixed-dimensional representation. The resulting acoustic word embeddings can form the basis of search, discovery, and indexing systems for low- and…

Audio and Speech Processing · Electrical Eng. & Systems 2020-12-07 Puyuan Peng , Herman Kamper , Karen Livescu

Acoustic word embeddings --- fixed-dimensional vector representations of variable-length spoken word segments --- have begun to be considered for tasks such as speech recognition and query-by-example search. Such embeddings can be learned…

Computation and Language · Computer Science 2016-11-09 Shane Settle , Karen Livescu

In this paper, we propose a visual embedding approach to improving embedding aware speech enhancement (EASE) by synchronizing visual lip frames at the phone and place of articulation levels. We first extract visual embedding from lip frames…

Sound · Computer Science 2020-09-22 Hang Chen , Jun Du , Yu Hu , Li-Rong Dai , Bao-Cai Yin , Chin-Hui Lee

Acoustic word embeddings are typically created by training a pooling function using pairs of word-like units. For unsupervised systems, these are mined using k-nearest neighbor (KNN) search, which is slow. Recently, mean-pooled…

Computation and Language · Computer Science 2023-06-06 Ramon Sanabria , Ondrej Klejch , Hao Tang , Sharon Goldwater

Discrete audio tokens derived from self-supervised learning models have gained widespread usage in speech generation. However, current practice of directly utilizing audio tokens poses challenges for sequence modeling due to the length of…

Sound · Computer Science 2024-01-17 Feiyu Shen , Yiwei Guo , Chenpeng Du , Xie Chen , Kai Yu

Using audio and text embeddings jointly for Keyword Spotting (KWS) has shown high-quality results, but the key challenge of how to semantically align two embeddings for multi-word keywords of different sequence lengths remains largely…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-09 Kumari Nishu , Minsik Cho , Devang Naik

Cloud computing is emerging as a revolutionary computing paradigm which pro-vides a flexible and economic strategy for data management and resource sharing. Security and privacy become major concerns in the cloud scenario, for which…

Information Retrieval · Computer Science 2017-09-01 Ruihui Zhao , Mizuho Iwaihara

In settings where only unlabelled speech data is available, speech technology needs to be developed without transcriptions, pronunciation dictionaries, or language modelling text. A similar problem is faced when modelling infant language…

Computation and Language · Computer Science 2016-03-10 Herman Kamper , Aren Jansen , Sharon Goldwater

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

Recent advances in cross-lingual word embeddings have primarily relied on mapping-based methods, which project pretrained word embeddings from different languages into a shared space through a linear transformation. However, these…

Computation and Language · Computer Science 2020-05-04 Ali Sabet , Prakhar Gupta , Jean-Baptiste Cordonnier , Robert West , Martin Jaggi

We investigate unsupervised models that can map a variable-duration speech segment to a fixed-dimensional representation. In settings where unlabelled speech is the only available resource, such acoustic word embeddings can form the basis…

Computation and Language · Computer Science 2019-04-16 Herman Kamper

Developing speech technologies for low-resource languages has become a very active research field over the last decade. Among others, Bayesian models have shown some promising results on artificial examples but still lack of in situ…

Recent speaker diarisation systems often convert variable length speech segments into fixed-length vector representations for speaker clustering, which are known as speaker embeddings. In this paper, the content-aware speaker embeddings…

Sound · Computer Science 2021-02-15 G. Sun , D. Liu , C. Zhang , P. C. Woodland

Recent work has begun exploring neural acoustic word embeddings---fixed-dimensional vector representations of arbitrary-length speech segments corresponding to words. Such embeddings are applicable to speech retrieval and recognition tasks,…

Computation and Language · Computer Science 2017-03-14 Wanjia He , Weiran Wang , Karen Livescu