English
Related papers

Related papers: Exploring a Unified Attention-Based Pooling Framew…

200 papers

Most state-of-the-art Deep Learning systems for speaker verification are based on speaker embedding extractors. These architectures are commonly composed of a feature extractor front-end together with a pooling layer to encode…

Audio and Speech Processing · Electrical Eng. & Systems 2021-01-12 Miquel India , Pooyan Safari , Javier Hernando

State-of-the-art Deep Learning systems for speaker verification are commonly based on speaker embedding extractors. These architectures are usually composed of a feature extractor front-end together with a pooling layer to encode…

Audio and Speech Processing · Electrical Eng. & Systems 2024-05-08 Federico Costa , Miquel India , Javier Hernando

This paper proposes attentive statistics pooling for deep speaker embedding in text-independent speaker verification. In conventional speaker embedding, frame-level features are averaged over all the frames of a single utterance to form an…

Audio and Speech Processing · Electrical Eng. & Systems 2019-02-27 Koji Okabe , Takafumi Koshinaka , Koichi Shinoda

This paper proposes a serialized multi-layer multi-head attention for neural speaker embedding in text-independent speaker verification. In prior works, frame-level features from one layer are aggregated to form an utterance-level…

Sound · Computer Science 2021-07-15 Hongning Zhu , Kong Aik Lee , Haizhou Li

Recent speaker verification studies have achieved notable success by leveraging layer-wise output from pre-trained Transformer models. However, few have explored the advancements in aggregating these multi-level features beyond the static…

Sound · Computer Science 2025-12-30 Jin Sob Kim , Hyun Joon Park , Wooseok Shin , Sung Won Han

Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…

Sound · Computer Science 2019-07-03 Miquel India , Pooyan Safari , Javier Hernando

This paper proposes a method for extracting speaker embedding for each speaker from a variable-length recording containing multiple speakers. Speaker embeddings are crucial not only for speaker recognition but also for various multi-speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-02 Shota Horiguchi , Atsushi Ando , Takafumi Moriya , Takanori Ashihara , Hiroshi Sato , Naohiro Tawara , Marc Delcroix

Pooling is an essential component of a wide variety of sentence representation and embedding models. This paper explores generalized pooling methods to enhance sentence embedding. We propose vector-based multi-head attention that includes…

Computation and Language · Computer Science 2022-02-24 Qian Chen , Zhen-Hua Ling , Xiaodan Zhu

With the advent of general-purpose speech representations from large-scale self-supervised models, applying a single model to multiple downstream tasks is becoming a de-facto approach. However, the pooling problem remains; the length of…

Machine Learning · Computer Science 2023-04-11 Jeongkyun Park , Kwanghee Choi , Hyunjun Heo , Hyung-Min Park

Recent studies have shown that frame-level deep speaker features can be derived from a deep neural network with the training target set to discriminate speakers by a short speech segment. By pooling the frame-level features, utterance-level…

Audio and Speech Processing · Electrical Eng. & Systems 2018-11-09 Lantian Li , Zhiyuan Tang , Ying Shi , Dong Wang

Most recent speaker verification systems are based on extracting speaker embeddings using a deep neural network. The pooling layer in the network aims to aggregate frame-level features extracted by the backbone. In this paper, we propose a…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-12 Yufeng Ma , Yiwei Ding , Miao Zhao , Yu Zheng , Min Liu , Minqiang Xu

The x-vector architecture has recently achieved state-of-the-art results on the speaker verification task. This architecture incorporates a central layer, referred to as temporal pooling, which stacks statistical parameters of the acoustic…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-11 Mickael Rouvier , Pierre-Michel Bousquet , Jarod Duret

Pooling is needed to aggregate frame-level features into utterance-level representations for speaker modeling. Given the success of statistics-based pooling methods, we hypothesize that speaker characteristics are well represented in the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-28 Yusheng Tian , Jingyu Li , Tan Lee

We propose an approach to extract speaker embeddings that are robust to speaking style variations in text-independent speaker verification. Typically, speaker embedding extraction includes training a DNN for speaker classification and using…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-29 Amber Afshan , Abeer Alwan

The goal of this paper is text-independent speaker verification where utterances come from 'in the wild' videos and may contain irrelevant signal. While speaker verification is naturally a pair-wise problem, existing methods to produce the…

Audio and Speech Processing · Electrical Eng. & Systems 2020-12-04 Seong Min Kye , Yoohwan Kwon , Joon Son Chung

This paper proposes a multi-task learning network with phoneme-aware and channel-wise attentive learning strategies for text-dependent Speaker Verification (SV). In the proposed structure, the frame-level multi-task learning along with the…

Sound · Computer Science 2021-06-28 Yan Liu , Zheng Li , Lin Li , Qingyang Hong

Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire…

Audio and Speech Processing · Electrical Eng. & Systems 2018-02-02 F A Rezaur Rahman Chowdhury , Quan Wang , Ignacio Lopez Moreno , Li Wan

This paper aims to improve the widely used deep speaker embedding x-vector model. We propose the following improvements: (1) a hybrid neural network structure using both time delay neural network (TDNN) and long short-term memory neural…

Computation and Language · Computer Science 2019-02-22 Yun Tang , Guohong Ding , Jing Huang , Xiaodong He , Bowen Zhou

State-of-the-art transformer models for Speech Emotion Recognition (SER) rely on temporal feature aggregation, yet advanced pooling methods remain underexplored. We systematically benchmark pooling strategies, including Multi-Query…

Pooling is one of the main elements in convolutional neural networks. The pooling reduces the size of the feature map, enabling training and testing with a limited amount of computation. This paper proposes a new pooling method named…

Computer Vision and Pattern Recognition · Computer Science 2019-07-29 Junhyuk Hyun , Hongje Seong , Euntai Kim
‹ Prev 1 2 3 10 Next ›