English
Related papers

Related papers: Probabilistic Permutation Invariant Training for S…

200 papers

The cocktail party problem comprises the challenging task of understanding a speech signal in a complex acoustic environment, where multiple speakers and background noise signals simultaneously interfere with the speech signal of interest.…

Sound · Computer Science 2018-12-05 Morten Kolbæk

In recent years, rapid progress has been made on the problem of single-channel sound separation using supervised training of deep neural networks. In such supervised approaches, a model is trained to predict the component sources from…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-27 Scott Wisdom , Efthymios Tzinis , Hakan Erdogan , Ron J. Weiss , Kevin Wilson , John R. Hershey

Dynamic sparsity, where the sparsity patterns are unknown until runtime, poses a significant challenge to deep learning. The state-of-the-art sparsity-aware deep learning solutions are restricted to pre-defined, static sparsity patterns due…

Usable speech criteria are proposed to extract minimally corrupted speech for speaker identification (SID) in co-channel speech. In co-channel speech, either speaker can randomly appear as the stronger speaker or the weaker one at a time.…

Sound · Computer Science 2013-01-03 Wajdi Ghezaiel , Amel Ben Slimane , Ezzedine Ben Braiek

Weight tying is widely used in compact language models to reduce parameters by sharing the token table between the input embedding and the output projection. However, parameter sharing alone does not guarantee a stable token interface:…

Computation and Language · Computer Science 2026-05-11 Jian Gu , Aldeida Aleti , Chunyang Chen , Hongyu Zhang

Mechanisms for continued self-improvement of language models without external supervision remain an open challenge. We propose Peer-Predictive Self-Training (PST), a label-free fine-tuning framework in which multiple language models improve…

Computation and Language · Computer Science 2026-04-28 Shi Feng , Hanlin Zhang , Fan Nie , Sham Kakade , Yiling Chen

We propose RemixIT, a simple and novel self-supervised training method for speech enhancement. The proposed method is based on a continuously self-training scheme that overcomes limitations from previous studies including assumptions for…

Sound · Computer Science 2022-11-14 Efthymios Tzinis , Yossi Adi , Vamsi K. Ithapu , Buye Xu , Anurag Kumar

Supervised neural network training has led to significant progress on single-channel sound separation. This approach relies on ground truth isolated sources, which precludes scaling to widely available mixture data and limits progress on…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-19 Scott Wisdom , Aren Jansen , Ron J. Weiss , Hakan Erdogan , John R. Hershey

Prompt Learning has recently gained great popularity in bridging the gap between pretraining tasks and various downstream tasks. It freezes Pretrained Language Models (PLMs) and only tunes a few task-related parameters (prompts) for…

Computation and Language · Computer Science 2022-06-07 Yuezihan Jiang , Hao Yang , Junyang Lin , Hanyu Zhao , An Yang , Chang Zhou , Hongxia Yang , Zhi Yang , Bin Cui

Language-audio joint representation learning frameworks typically depend on deterministic embeddings, assuming a one-to-one correspondence between audio and text. In real-world settings, however, the language-audio relationship is…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-22 Toranosuke Manabe , Yuchi Ishikawa , Hokuto Munakata , Tatsuya Komatsu

Speech separation seeks to separate individual speech signals from a speech mixture. Typically, most separation models are trained on synthetic data due to the unavailability of target reference in real-world cocktail party scenarios. As a…

Sound · Computer Science 2024-11-06 Wupeng Wang , Zexu Pan , Xinke Li , Shuai Wang , Haizhou Li

We introduce a new approach for speech pre-training named SPIRAL which works by learning denoising representation of perturbed data in a teacher-student framework. Specifically, given a speech utterance, we first feed the utterance to a…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-08 Wenyong Huang , Zhenhe Zhang , Yu Ting Yeung , Xin Jiang , Qun Liu

Pre-trained self-supervised models such as BERT have achieved striking success in learning sequence representations, especially for natural language processing. These models typically corrupt the given sequences with certain types of noise,…

Computation and Language · Computer Science 2020-11-02 Fuli Luo , Pengcheng Yang , Shicheng Li , Xuancheng Ren , Xu Sun

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

Punctuation prediction for automatic speech recognition (ASR) output transcripts plays a crucial role for improving the readability of the ASR transcripts and for improving the performance of downstream natural language processing…

Computation and Language · Computer Science 2021-09-02 Qian Chen , Wen Wang , Mengzhe Chen , Qinglin Zhang

Universal sound separation (USS) is a task to separate arbitrary sounds from an audio mixture. Existing USS systems are capable of separating arbitrary sources, given a few examples of the target sources as queries. However, separating…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-01 Yuzhuo Liu , Xubo Liu , Yan Zhao , Yuanyuan Wang , Rui Xia , Pingchuan Tain , Yuxuan Wang

We consider the problem of training speech recognition systems without using any labeled data, under the assumption that the learner can only access to the input utterances and a phoneme language model estimated from a non-overlapping…

Audio and Speech Processing · Electrical Eng. & Systems 2018-12-27 Chih-Kuan Yeh , Jianshu Chen , Chengzhu Yu , Dong Yu

In conventional supervised pattern recognition tasks, model selection is typically accomplished by minimizing the classification error rate on a set of so-called development data, subject to ground-truth labeling by human experts or some…

Machine Learning · Statistics 2011-08-25 Christopher M. White , Sanjeev P. Khudanpur , Patrick J. Wolfe

Many of the recent advances in speech separation are primarily aimed at synthetic mixtures of short audio utterances with high degrees of overlap. Most of these approaches need an additional stitching step to stitch the separated speech…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-07 Rohit Paturi , Sundararajan Srinivasan , Katrin Kirchhoff , Daniel Garcia-Romero

Prompt-based learning is susceptible to intrinsic bias present in pre-trained language models (LMs), leading to sub-optimal performance in prompt-based zero/few-shot settings. In this work, we propose a null-input prompting method to…

Computation and Language · Computer Science 2024-10-08 Kang He , Yinghan Long , Kaushik Roy