English
Related papers

Related papers: Disentangled Speaker Representation Learning via M…

200 papers

Feature extraction plays an important role as a front-end processing block in speaker identification (SI) process. Most of the SI systems utilize like Mel-Frequency Cepstral Coefficients (MFCC), Perceptual Linear Prediction (PLP), Linear…

Sound · Computer Science 2015-03-19 Md. Sahidullah , Sandipan Chakroborty , Goutam Saha

One of the fundamental representation learning tasks is unsupervised sequential disentanglement, where latent codes of inputs are decomposed to a single static factor and a sequence of dynamic factors. To extract this latent information,…

Machine Learning · Computer Science 2025-10-09 Nimrod Berman , Ilan Naiman , Idan Arbiv , Gal Fadlon , Omri Azencot

In multi-speaker applications is common to have pre-computed models from enrolled speakers. Using these models to identify the instances in which these speakers intervene in a recording is the task of speaker tracking. In this paper, we…

Speaker clustering is the task of identifying the unique speakers in a set of audio recordings (each belonging to exactly one speaker) without knowing who and how many speakers are present in the entire data, which is essential for speaker…

Sound · Computer Science 2025-09-30 Chaohao Lin , Xu Zheng , Kaida Wu , Peihao Xiang , Ou Bai

When dealing with overlapped speech, the performance of automatic speech recognition (ASR) systems substantially degrades as they are designed for single-talker speech. To enhance ASR performance in conversational or meeting environments,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-16 Hassan Taherian , DeLiang Wang

Self-supervised speaker embeddings are widely used in speaker verification systems, but prior work has shown that they often encode sensitive demographic attributes, raising fairness and privacy concerns. This paper investigates the extent…

Deep clustering (DC) and utterance-level permutation invariant training (uPIT) have been demonstrated promising for speaker-independent speech separation. DC is usually formulated as two-step processes: embedding learning and embedding…

Sound · Computer Science 2019-07-24 Cunhang Fan , Bin Liu , Jianhua Tao , Jiangyan Yi , Zhengqi Wen

In recent years, the remarkable advancements in deep neural networks have brought tremendous convenience. However, the training process of a highly effective model necessitates a substantial quantity of samples, which brings huge potential…

Sound · Computer Science 2024-09-13 Zhisheng Zhang , Pengyang Huang

Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have…

Sound · Computer Science 2018-05-16 Hiroshi Seki , Takaaki Hori , Shinji Watanabe , Jonathan Le Roux , John R. Hershey

We present an end-to-end deep network model that performs meeting diarization from single-channel audio recordings. End-to-end diarization models have the advantage of handling speaker overlap and enabling straightforward handling of…

Sound · Computer Science 2021-05-06 Soumi Maiti , Hakan Erdogan , Kevin Wilson , Scott Wisdom , Shinji Watanabe , John R. Hershey

This research addresses the problem of acoustic modeling of low-resource languages for which transcribed training data is absent. The goal is to learn robust frame-level feature representations that can be used to identify and distinguish…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-01 Siyuan Feng , Tan Lee

We propose an unsupervised learning method to disentangle speech into content representation and speaker identity representation. We apply this method to the challenging one-shot cross-lingual voice conversion task to demonstrate the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-26 Hui Lu , Disong Wang , Xixin Wu , Zhiyong Wu , Xunying Liu , Helen Meng

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

Training machines to understand natural language and interact with humans is one of the major goals of artificial intelligence. Recent years have witnessed an evolution from matching networks to pre-trained language models (PrLMs). In…

Computation and Language · Computer Science 2023-01-12 Zhuosheng Zhang , Hai Zhao , Longxiang Liu

Overlapping speech diarization is always treated as a multi-label classification problem. In this paper, we reformulate this task as a single-label prediction problem by encoding the multi-speaker labels with power set. Specifically, we…

Sound · Computer Science 2021-11-30 Zhihao Du , Shiliang Zhang , Siqi Zheng , Weilong Huang , Ming Lei

Recently, deep clustering (DPCL) based speaker-independent speech separation has drawn much attention, since it needs little speaker prior information. However, it still has much room of improvement, particularly in reverberant…

Sound · Computer Science 2019-10-25 Ziye Yang , Xiao-Lei Zhang

Recently, speaker embeddings extracted from a speaker discriminative deep neural network (DNN) yield better performance than the conventional methods such as i-vector. In most cases, the DNN speaker classifier is trained using cross entropy…

Audio and Speech Processing · Electrical Eng. & Systems 2019-06-19 Xu Xiang , Shuai Wang , Houjun Huang , Yanmin Qian , Kai Yu

To highlight the challenges of achieving representation disentanglement for text domain in an unsupervised setting, in this paper we select a representative set of successfully applied models from the image domain. We evaluate these models…

Computation and Language · Computer Science 2021-06-08 Lan Zhang , Victor Prokhorov , Ehsan Shareghi

Mismatch between enrollment and test conditions causes serious performance degradation on speaker recognition systems. This paper presents a statistics decomposition (SD) approach to solve this problem. This approach decomposes the PLDA…

Sound · Computer Science 2021-11-25 Lantian Li , Dong Wang , Jiawen Kang , Renyu Wang , Jing Wu , Zhendong Gao , Xiao Chen

Since the first speech recognition systems were built more than 30 years ago, improvement in voice technology has enabled applications such as smart assistants and automated customer support. However, conversation intelligence of the future…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-15 Desh Raj