English
Related papers

Related papers: S-vectors and TESA: Speaker Embeddings and a Speak…

200 papers

Mechanisms for encoding positional information are central for transformer-based language models. In this paper, we analyze the position embeddings of existing language models, finding strong evidence of translation invariance, both for the…

Computation and Language · Computer Science 2021-06-04 Ulme Wennberg , Gustav Eje Henter

Voice activity detection (VAD) is essential in speech-based systems, but traditional methods detect only speech presence without identifying speakers. Target-speaker VAD (TS-VAD) extends this by detecting the speech of a known speaker using…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-16 Wen-Yung Wu , Pei-Chin Hsieh , Tai-Shih Chi

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-02 Zili Huang , Desh Raj , Paola García , Sanjeev Khudanpur

Learning speaker turn embeddings has shown considerable improvement in situations where conventional speaker modeling approaches fail. However, this improvement is relatively limited when compared to the gain observed in face embedding…

Computer Vision and Pattern Recognition · Computer Science 2017-07-11 Nam Le , Jean-Marc Odobez

The Transformer self-attention network has recently shown promising performance as an alternative to recurrent neural networks in end-to-end (E2E) automatic speech recognition (ASR) systems. However, Transformer has a drawback in that the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-29 Emiru Tsunoo , Yosuke Kashiwagi , Toshiyuki Kumakura , Shinji Watanabe

End-to-end neural diarization with encoder-decoder based attractors (EEND-EDA) is a method to perform diarization in a single neural network. EDA handles the diarization of a flexible number of speakers by using an LSTM-based…

Sound · Computer Science 2023-12-12 Lahiru Samarakoon , Samuel J. Broughton , Marc Härkönen , Ivan Fung

The Transformer has shown impressive performance in automatic speech recognition. It uses the encoder-decoder structure with self-attention to learn the relationship between the high-level representation of the source inputs and embedding…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-16 Xinyuan Zhou , Grandee Lee , Emre Yılmaz , Yanhua Long , Jiaen Liang , Haizhou Li

Unsupervised speech disentanglement aims at separating fast varying from slowly varying components of a speech signal. In this contribution, we take a closer look at the embedding vector representing the slowly varying signal components,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-20 Frederik Rautenberg , Michael Kuhlmann , Jana Wiechmann , Fritz Seebauer , Petra Wagner , Reinhold Haeb-Umbach

Speaker embeddings (x-vectors) extracted from very short segments of speech have recently been shown to give competitive performance in speaker diarization. We generalize this recipe by extracting from each speech segment, in parallel with…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-09 Anna Silnova , Niko Brümmer , Johan Rohdin , Themos Stafylakis , Lukáš Burget

In general, a self-attention mechanism has been applied for speaker embedding encoding. Previous studies focused on training the self-attention in a high-level layer, such as the last pooling layer. However, the effect of low-level features…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-29 Soonshin Seo , Ji-Hwan Kim

The x-vector based deep neural network (DNN) embedding systems have demonstrated effectiveness for text-independent speaker verification. This paper presents a multi-task learning architecture for training the speaker embedding DNN with the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-04-05 Lanhua You , Wu Guo , Lirong Dai , Jun Du

Speaker embedding has been a fundamental feature for speaker-related tasks such as verification, clustering, and diarization. Traditionally, speaker embeddings are represented as fixed vectors in high-dimensional space. This could lead to…

Sound · Computer Science 2022-06-28 Siqi Zheng , Hongbin Suo , Qian Chen

Deep speaker embeddings have become the leading method for encoding speaker identity in speaker recognition tasks. The embedding space should ideally capture the variations between all possible speakers, encoding the multiple acoustic…

Sound · Computer Science 2021-04-26 Chau Luu , Peter Bell , Steve Renals

Self-supervised learned models have been found to be very effective for certain speech tasks such as automatic speech recognition, speaker identification, keyword spotting and others. While the features are undeniably useful in speech…

Audio and Speech Processing · Electrical Eng. & Systems 2024-03-05 Ravi Shankar , Ke Tan , Buye Xu , Anurag Kumar

Automatic Audio Captioning (AAC) refers to the task of translating audio into a natural language that describes the audio events, source of the events and their relationships. The limited samples in AAC datasets at present, has set up a…

Sound · Computer Science 2022-02-01 Swapnil Bhosale , Rupayan Chakraborty , Sunil Kumar Kopparapu

We present a Bayesian formulation for deep speaker embedding, wherein the xi-vector is the Bayesian counterpart of the x-vector, taking into account the uncertainty estimate. On the technology front, we offer a simple and straightforward…

Audio and Speech Processing · Electrical Eng. & Systems 2021-08-13 Kong Aik Lee , Qiongqiong Wang , Takafumi Koshinaka

This study evaluates the performance of three advanced speech encoder models, Wav2Vec 2.0, XLS-R, and Whisper, in speaker identification tasks. By fine-tuning these models and analyzing their layer-wise representations using SVCCA, k-means…

Sound · Computer Science 2025-09-30 Linus Stuhlmann , Michael Alexander Saxer

How do speech models trained through self-supervised learning structure their representations? Previous studies have looked at how information is encoded in feature vectors across different layers. But few studies have considered whether…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-11 Kyle Janse van Rensburg , Benjamin van Niekerk , Herman Kamper

Target speaker extraction (TSE) relies on a reference cue of the target to extract the target speech from a speech mixture. While a speaker embedding is commonly used as the reference cue, such embedding pre-trained with a large number of…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-12 Ke Zhang , Junjie Li , Shuai Wang , Yangjie Wei , Yi Wang , Yannan Wang , Haizhou Li

One-shot voice conversion has received significant attention since only one utterance from source speaker and target speaker respectively is required. Moreover, source speaker and target speaker do not need to be seen during training.…

Sound · Computer Science 2021-06-22 Hongqiang Du , Lei Xie
‹ Prev 1 3 4 5 6 7 10 Next ›