English
Related papers

Related papers: Collar-aware Training for Streaming Speaker Change…

200 papers

Replacing hand-engineered pipelines with end-to-end deep learning systems has enabled strong results in applications like speech and object recognition. However, the causality and latency constraints of production systems put end-to-end…

This paper presents a linear regression based back-end for speaker verification. Linear regression is a simple linear model that minimizes the mean squared estimation error between the target and its estimate with a closed form solution,…

Sound · Computer Science 2018-02-13 Xiao-Lei Zhang

We introduce and analyze a novel approach to the problem of speaker identification in multi-party recorded meetings. Given a speech segment and a set of available candidate profiles, we propose a novel data-driven way to model the distance…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-23 Nikolaos Flemotomos , Dimitrios Dimitriadis

In this study, we introduce a novel cross-modal retrieval task involving speaker descriptions and their corresponding audio samples. Utilizing pre-trained speaker and text encoders, we present a simple learning framework based on…

Sound · Computer Science 2023-12-12 Xuechen Liu , Xin Wang , Erica Cooper , Xiaoxiao Miao , Junichi Yamagishi

Speaker diarization systems are challenged by a trade-off between the temporal resolution and the fidelity of the speaker representation. By obtaining a superior temporal resolution with an enhanced accuracy, a multi-scale approach is a way…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-31 Tae Jin Park , Nithin Rao Koluguri , Jagadeesh Balam , Boris Ginsburg

Speaker identification typically involves three stages. First, a front-end speaker embedding model is trained to embed utterance and speaker profiles. Second, a scoring function is applied between a runtime utterance and each speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-22 Zhenning Tan , Yuguang Yang , Eunjung Han , Andreas Stolcke

Transformer-based end-to-end neural speaker diarization (EEND) models utilize the multi-head self-attention (SA) mechanism to enable accurate speaker label prediction in overlapped speech regions. In this study, to enhance the training…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-03 Ye-Rin Jeoung , Joon-Young Yang , Jeong-Hwan Choi , Joon-Hyuk Chang

Active speaker detection (ASD) is a multi-modal task that aims to identify who, if anyone, is speaking from a set of candidates. Current audio-visual approaches for ASD typically rely on visually pre-extracted face tracks (sequences of…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-08 Davide Berghi , Adrian Hilton , Philip J. B. Jackson

The deep learning models used for speaker verification rely heavily on large amounts of data and correct labeling. However, noisy (incorrect) labels often occur, which degrades the performance of the system. In this paper, we propose a…

Sound · Computer Science 2026-04-29 Zhihua Fang , Liang He , Hanhan Ma , Xiaochen Guo , Lin Li

An important problem in machine auditory perception is to recognize and detect sound events. In this paper, we propose a sequential self-teaching approach to learning sounds. Our main proposition is that it is harder to learn sounds in…

Sound · Computer Science 2020-07-02 Anurag Kumar , Vamsi Krishna Ithapu

This paper introduces an active learning (AL) framework for anomalous sound detection (ASD) in machine condition monitoring system. Typically, ASD models are trained solely on normal samples due to the scarcity of anomalous data, leading to…

Sound · Computer Science 2024-08-13 Tuan Vu Ho , Kota Dohi , Yohei Kawaguchi

Our objective is an audio-visual model for separating a single speaker from a mixture of sounds such as other speakers and background noise. Moreover, we wish to hear the speaker even when the visual cues are temporarily absent due to…

Computer Vision and Pattern Recognition · Computer Science 2019-07-12 Triantafyllos Afouras , Joon Son Chung , Andrew Zisserman

This paper proposes an improved approach for open-set speaker identification based on pretrained speaker foundation models. Building upon the previous Speaker Reciprocal Points Learning framework (V1), we first introduce an enhanced…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-16 Zhiyong Chen , Shuhang Wu , Yingjie Duan , Xinkang Xu , Xinhui Hu

We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed-size speaker embedding from a spoken utterance…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-28 Ruijie Tao , Kong Aik Lee , Rohan Kumar Das , Ville Hautamäki , Haizhou Li

Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available. Most of these works consider that labels obtained from the annotator are…

Computer Vision and Pattern Recognition · Computer Science 2020-10-20 Sudipta Paul , Shivkumar Chandrasekaran , B. S. Manjunath , Amit K. Roy-Chowdhury

Single-channel speech enhancement approaches do not always improve automatic recognition rates in the presence of noise, because they can introduce distortions unhelpful for recognition. Following a trend towards end-to-end training of…

Sound · Computer Science 2021-12-14 Peter Plantinga , Deblin Bagchi , Eric Fosler-Lussier

Turn-taking has played an essential role in structuring the regulation of a conversation. The task of identifying the main speaker (who is properly taking his/her turn of speaking) and the interrupters (who are interrupting or reacting to…

Computer Vision and Pattern Recognition · Computer Science 2021-08-29 Thanh-Dat Truong , Chi Nhan Duong , The De Vu , Hoang Anh Pham , Bhiksha Raj , Ngan Le , Khoa Luu

Natural language processing (NLP) models trained on people-generated data can be unreliable because, without any constraints, they can learn from spurious correlations that are not relevant to the task. We hypothesize that enriching models…

Computation and Language · Computer Science 2022-03-18 Alissa Ostapenko , Shuly Wintner , Melinda Fricke , Yulia Tsvetkov

Recent research shows end-to-end ASR systems can recognize overlapped speech from multiple speakers. However, all published works have assumed no latency constraints during inference, which does not hold for most voice assistant…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-22 Ilya Sklyar , Anna Piunova , Yulan Liu

In this paper we present a Transformer-Transducer model architecture and a training technique to unify streaming and non-streaming speech recognition models into one model. The model is composed of a stack of transformer layers for audio…

Sound · Computer Science 2020-10-08 Anshuman Tripathi , Jaeyoung Kim , Qian Zhang , Han Lu , Hasim Sak
‹ Prev 1 4 5 6 7 8 10 Next ›