English
Related papers

Related papers: Self-supervised Speaker Recognition Training Using…

200 papers

Recent efforts in Spoken Dialogue Modeling aim to synthesize spoken dialogue without the need for direct transcription, thereby preserving the wealth of non-textual information inherent in speech. However, this approach faces a challenge…

Computation and Language · Computer Science 2024-07-03 Yu-Kuan Fu , Cheng-Kuang Lee , Hsiu-Hsuan Wang , Hung-yi Lee

The cost of annotating transcriptions for large speech corpora becomes a bottleneck to maximally enjoy the potential capacity of deep neural network-based automatic speech recognition models. In this paper, we present a new training…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-06 Jihwan Bang , Heesu Kim , YoungJoon Yoo , Jung-Woo Ha

On-device Automatic Speech Recognition (ASR) models trained on speech data of a large population might underperform for individuals unseen during training. This is due to a domain shift between user data and the original training data,…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-23 Jisi Zhang , Vandana Rajan , Haaris Mehmood , David Tuckey , Pablo Peso Parada , Md Asif Jalal , Karthikeyan Saravanan , Gil Ho Lee , Jungin Lee , Seokyeong Jung

Source separation can improve automatic speech recognition (ASR) under multi-party meeting scenarios by extracting single-speaker signals from overlapped speech. Despite the success of self-supervised learning models in single-channel…

Audio and Speech Processing · Electrical Eng. & Systems 2023-04-04 Yuang Li , Xianrui Zheng , Philip C. Woodland

Self-supervised learning (SSL) has been able to leverage unlabeled data to boost the performance of automatic speech recognition (ASR) models when we have access to only a small amount of transcribed speech data. However, this raises the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-12-06 Reem Gody , David Harwath

Supervised learning methods have shown effectiveness in estimating spatial acoustic parameters such as time difference of arrival, direct-to-reverberant ratio and reverberation time. However, they still suffer from the simulation-to-reality…

Sound · Computer Science 2024-09-10 Bing Yang , Xiaofei Li

Recently, fine-tuning large pre-trained Transformer models using downstream datasets has received a rising interest. Despite their success, it is still challenging to disentangle the benefits of large-scale datasets and Transformer…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-19 Junyi Peng , Oldřich Plchot , Themos Stafylakis , Ladislav Mošner , Lukáš Burget , Jan Černocký

We present a simple and effective self-supervised learning approach for speech recognition. The approach learns a model to predict the masked speech signals, in the form of discrete labels generated with a random-projection quantizer. In…

Computation and Language · Computer Science 2022-07-01 Chung-Cheng Chiu , James Qin , Yu Zhang , Jiahui Yu , Yonghui Wu

In this paper, we address the problem of speaker recognition in challenging acoustic conditions using a novel method to extract robust speaker-discriminative speech representations. We adopt a recently proposed unsupervised adversarial…

Audio and Speech Processing · Electrical Eng. & Systems 2019-11-05 Raghuveer Peri , Monisankha Pal , Arindam Jati , Krishna Somandepalli , Shrikanth Narayanan

There is growing interest in the automated extraction of relevant information from clinical dialogues. However, it is difficult to collect and construct large annotated resources for clinical dialogue tasks. Recent developments in natural…

Computation and Language · Computer Science 2022-06-07 Zhengyuan Liu , Pavitra Krishnaswamy , Nancy F. Chen

Much recent work on Spoken Language Understanding (SLU) is limited in at least one of three ways: models were trained on oracle text input and neglected ASR errors, models were trained to predict only intents without the slot values, or…

Computation and Language · Computer Science 2020-10-28 Cheng-I Lai , Yung-Sung Chuang , Hung-Yi Lee , Shang-Wen Li , James Glass

Most previous neural text-to-speech (TTS) methods are mainly based on supervised learning methods, which means they depend on a large training dataset and hard to achieve comparable performance under low-resource conditions. To address this…

Sound · Computer Science 2022-10-27 Xulong Zhang , Jianzong Wang , Ning Cheng , Jing Xiao

Iterative self-training, or iterative pseudo-labeling (IPL) -- using an improved model from the current iteration to provide pseudo-labels for the next iteration -- has proven to be a powerful approach to enhance the quality of speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-22 Zakaria Aldeneh , Takuya Higuchi , Jee-weon Jung , Li-Wei Chen , Stephen Shum , Ahmed Hussen Abdelaziz , Shinji Watanabe , Tatiana Likhomanenko , Barry-John Theobald

In this study, we investigate self-supervised representation learning for speaker verification (SV). First, we examine a simple contrastive learning approach (SimCLR) with a momentum contrastive (MoCo) learning framework, where the MoCo…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-16 Wei Xia , Chunlei Zhang , Chao Weng , Meng Yu , Dong Yu

Self-supervised learning (SSL) foundation models have emerged as powerful, domain-agnostic, general-purpose feature extractors applicable to a wide range of tasks. Such models pre-trained on human speech have demonstrated high…

Machine Learning · Computer Science 2025-01-22 Eklavya Sarkar , Mathew Magimai. -Doss

Target speech separation is the process of filtering a certain speaker's voice out of speech mixtures according to the additional speaker identity information provided. Recent works have made considerable improvement by processing signals…

Sound · Computer Science 2021-09-28 Qingjian Lin , Lin Yang , Xuyang Wang , Luyuan Xie , Chen Jia , Junjie Wang

This paper addresses user-specific dialogs. In contrast to previous research on personalized dialogue focused on achieving virtual user dialogue as defined by persona descriptions, user-specific dialogue aims to reproduce real-user dialogue…

Computation and Language · Computer Science 2024-09-04 Atsushi Otsuka , Kazuya Matsuo , Ryo Ishii , Narichika Nomoto , Hiroaki Sugiyama

Training deep networks with noisy labels leads to poor generalization and degraded accuracy due to overfitting to label noise. Existing approaches for learning with noisy labels often rely on the availability of a clean subset of data. By…

Machine Learning · Computer Science 2025-11-27 David Szczecina , Nicholas Pellegrino , Paul Fieguth

Recent work has shown that it is possible to train an $\textit{unsupervised}$ automatic speech recognition (ASR) system using only unpaired audio and text. Existing unsupervised ASR methods assume that no labeled data can be used for…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-19 Tatiana Likhomanenko , Loren Lugosch , Ronan Collobert

Speaker identification in the household scenario (e.g., for smart speakers) is typically based on only a few enrollment utterances but a much larger set of unlabeled data, suggesting semisupervised learning to improve speaker profiles. We…

Sound · Computer Science 2022-02-22 Long Chen , Venkatesh Ravichandran , Andreas Stolcke