English
Related papers

Related papers: Self Multi-Head Attention for Speaker Recognition

200 papers

We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple…

Sound · Computer Science 2018-04-27 Sergey Novoselov , Andrey Shulipa , Ivan Kremnev , Alexandr Kozlov , Vadim Shchemelinin

We present an approach to tackle the speaker recognition problem using Triplet Neural Networks. Currently, the $i$-vector representation with probabilistic linear discriminant analysis (PLDA) is the most commonly used technique to solve…

Sound · Computer Science 2019-10-07 Kin Wai Cheuk , Balamurali B. T. , Gemma Roig , Dorien Herremans

Speaker embeddings extracted with deep 2D convolutional neural networks are typically modeled as projections of first and second order statistics of channel-frequency pairs onto a linear layer, using either average or attentive pooling…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-08 Themos Stafylakis , Johan Rohdin , Lukas Burget

In speaker verification, the extraction of voice representations is mainly based on the Residual Neural Network (ResNet) architecture. ResNet is built upon convolution layers which learn filters to capture local spatial patterns along all…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-14 Mickael Rouvier , Pierre-Michel Bousquet

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

This paper proposes an online target speaker voice activity detection system for speaker diarization tasks, which does not require a priori knowledge from the clustering-based diarization system to obtain the target speaker embeddings. By…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-16 Weiqing Wang , Ming Li

The state-of-art approach to speaker verification involves the extraction of discriminative embeddings like x-vectors followed by a generative model back-end using a probabilistic linear discriminant analysis (PLDA). In this paper, we…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-10 Shreyas Ramoji , Prashant Krishnan , Prachi Singh , Sriram Ganapathy

The recent advances in deep learning are mostly driven by availability of large amount of training data. However, availability of such data is not always possible for specific tasks such as speaker recognition where collection of large…

Audio and Speech Processing · Electrical Eng. & Systems 2019-04-19 Prashant Anand , Ajeet Kumar Singh , Siddharth Srivastava , Brejesh Lall

Emotion recognition from speech is a challenging task. Re-cent advances in deep learning have led bi-directional recur-rent neural network (Bi-RNN) and attention mechanism as astandard method for speech emotion recognition, extractingand…

Sound · Computer Science 2021-06-09 Zixuan Peng , Yu Lu , Shengfeng Pan , Yunfeng Liu

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

In practical settings, a speaker recognition system needs to identify a speaker given a short utterance, while the enrollment utterance may be relatively long. However, existing speaker recognition models perform poorly with such short…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-12 Seong Min Kye , Youngmoon Jung , Hae Beom Lee , Sung Ju Hwang , Hoirin Kim

This work presents a novel back-end framework for speaker verification using graph attention networks. Segment-wise speaker embeddings extracted from multiple crops within an utterance are interpreted as node representations of a graph. The…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-09 Jee-weon Jung , Hee-Soo Heo , Ha-Jin Yu , Joon Son Chung

In recent years, self-supervised learning paradigm has received extensive attention due to its great success in various down-stream tasks. However, the fine-tuning strategies for adapting those pre-trained models to speaker verification…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-05 Junyi Peng , Oldrich Plchot , Themos Stafylakis , Ladislav Mosner , Lukas Burget , Jan Cernocky

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

Even though deep speaker models have demonstrated impressive accuracy in speaker verification tasks, this often comes at the expense of increased model size and computation time, presenting challenges for deployment in resource-constrained…

Sound · Computer Science 2023-12-21 Xuechen Liu , Md Sahidullah , Tomi Kinnunen

Many approaches can derive information about a single speaker's identity from the speech by learning to recognize consistent characteristics of acoustic parameters. However, it is challenging to determine identity information when there are…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-07 Hyewon Han , Soo-Whan Chung , Hong-Goo Kang

Modern automatic speaker verification relies largely on deep neural networks (DNNs) trained on mel-frequency cepstral coefficient (MFCC) features. While there are alternative feature extraction methods based on phase, prosody and long-term…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-31 Xuechen Liu , Md Sahidullah , Tomi Kinnunen

Recently deep neural networks (DNNs) have been used to learn speaker features. However, the quality of the learned features is not sufficiently good, so a complex back-end model, either neural or probabilistic, has to be used to address the…

Sound · Computer Science 2017-05-11 Lantian Li , Yixiang Chen , Ying Shi , Zhiyuan Tang , Dong Wang

The time delay neural network (TDNN) represents one of the state-of-the-art of neural solutions to text-independent speaker verification. However, they require a large number of filters to capture the speaker characteristics at any local…

Sound · Computer Science 2022-02-16 Tianchi Liu , Rohan Kumar Das , Kong Aik Lee , Haizhou Li

We propose a new method for speaker diarization that can handle overlapping speech with 2+ people. Our method is based on compositional embeddings [1]: Like standard speaker embedding methods such as x-vector [2], compositional embedding…

Sound · Computer Science 2021-02-11 Zeqian Li , Jacob Whitehill