检索结果-内蒙古大学图书馆

7th Conference on Machine Translation, WMT 2022

作者： Wicks, Rachel Post, Matt Center for Language and Speech Processing United States Human Language Technology Center of Excellence Johns Hopkins University United States

ISBN: (纸本)9781959429296

For the most part, NLP applications operate at the sentence level. Since sentences occur most naturally not on their own but embedded in documents, they must be extracted and segmented via the use of a segmenter, of which there are a handful of options. There has been some work evaluating the performance of segmenters on intrinsic metrics, that look at their ability to recover human-segmented sentence boundaries, but there has been no work looking at the effect of segmenters on downstream tasks. We ask the question, "does segmentation matter?" and attempt to answer it on the task of machine translation. We consider two settings: the inference scenario, where sentences are passed into a black-box system whose training segmentation is mostly unknown, and the training setting, where researchers have full control over the process. We find that the choice of segmenter largely does not matter, so long as its behavior is not one of extreme under- or over-segmentation. For such settings, we provide some qualitative analysis examining their harms, and point the way towards document-level processing. © 2022 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prototype based Masked Audio Model for Self-Supervised Learning of Sound Event Detection

Prototype based Masked Audio Model for Self-Supervised Learn...

引用

2025 IEEE International Conference on Acoustics, speech, and Signal processing, ICASSP 2025

作者： Cai, Pengfei Song, Yan Jiang, Nan Gu, Qing McLoughlin, Ian National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China China ICT Cluster Singapore Institute of Technology Singapore

ISBN: (纸本)9798350368741

A significant challenge in sound event detection (SED) is the effective utilization of unlabeled data, given the limited availability of labeled data due to high annotation costs. Semi-supervised algorithms rely on labeled data to learn from unlabeled data, and the performance is constrained by the quality and size of the former. In this paper, we introduce the Prototype based Masked Audio Model (PMAM) algorithm for self-supervised representation learning in SED, to better exploit unlabeled data. Specifically, semantically rich frame-level pseudo labels are constructed from a Gaussian mixture model (GMM) based prototypical distribution modeling. These pseudo labels supervise the leaning of a Transformer-based masked audio model, in which binary cross-entropy loss is employed instead of the widely used InfoNCE loss, to provide independent loss contributions from different prototypes, which is important in real scenarios in which multiple labels may apply to unsupervised data frames. A final stage of fine-tuning with just a small amount of labeled data yields a very high performing SED model. On like-for-like tests using the DESED task, our method achieves a PSDS1 score of 62.5%, surpassing current state-of-the-art models and demonstrating the superiority of the proposed technique. © 2025 IEEE.

关键词： masked audio model prototype self-supervised learning sound event detection

来源：评论

学校读者我要写书评

暂无评论

Exploring Representational Disparities Between Multilingual and Bilingual Translation Models

arXiv

引用

arXiv 2023年

作者： Verma, Neha Murray, Kenton Duh, Kevin Center for Language and Speech Processing Human Language Technology Center of Excellence

Multilingual machine translation has proven immensely useful for both parameter efficiency and overall performance across many language pairs via complete multilingual parameter sharing. However, some language pairs in multilingual models can see worse performance than in bilingual models, especially in the one-to-many translation setting. Motivated by their empirical differences, we examine the geometric differences in representations from bilingual models versus those from one-to-many multilingual models. Specifically, we compute the isotropy of these representations using intrinsic dimensionality and IsoScore, in order to measure how the representations utilize the dimensions in their underlying vector space. Using the same evaluation data in both models, we find that for a given language pair, its multilingual model decoder representations are consistently less isotropic and occupy fewer dimensions than comparable bilingual model decoder representations. Additionally, we show that much of the anisotropy in multilingual decoder representations can be attributed to modeling language-specific information, therefore limiting remaining representational capacity. Copyright © 2023, The Authors. All rights reserved.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

Deepfake Algorithm Recognition System with Augmented Data for ADD 2023 Challenge

Deepfake Algorithm Recognition System with Augmented Data fo...

引用

2023 Workshop on Deepfake Audio Detection and Analysis, DADA 2023

作者： Zeng, Xiao-Min Zhang, Jian-Tao Li, Kang Liu, Zhuo-Li Xie, Wei-Lin Song, Yan National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China Hefei China

In this paper, we describe our submitted systems to the ADD2023 Challenge Track 3–Deepfake algorithm recognition (AR). This task requires not only identifying known deepfake algorithms in closed-set but also distinguishing unknown algorithms. By closed-set classification experiments, we select the output of the pre-trained wav2vec2.0-base model as acoustic features. Then, we apply the ECAPA-TDNN model to recognize different deepfake algorithms and determine whether the samples belong to the unknown algorithms by threshold. Besides, we adopt data augmentation to improve the generalization and robustness of our model. We evaluate our system on the ADD2023 Challenge Track 3 and achieve a 75.41% F1-score. Our submission ranked third in the deepfake algorithm recognition track of the ADD2023 Challenge. © 2023 CEUR-WS. All rights reserved.

关键词： data augmentation deepfake algorithm recognition open-set recognition

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Personalized Lip-To-speech Synthesis with Face Image Based Voice Control 48

Zero-Shot Personalized Lip-To-Speech Synthesis with Face Ima...

引用

48th IEEE International Conference on Acoustics, speech and Signal processing, ICASSP 2023

作者： Sheng, Zheng-Yan Ai, Yang Ling, Zhen-Hua University of Science and Technology of China National Engineering Research Center of Speech and Language Information Processing Hefei China

ISBN: (纸本)9781728163277

Lip-to-speech (Lip2speech) synthesis, which predicts corresponding speech from talking face images, has witnessed significant progress with various models and training strategies in a series of independent studies. However, existing studies can not achieve voice control under zero-shot condition, because extra speaker embeddings need to be extracted from natural reference speech and are unavailable when only the silent video of an unseen speaker is given. In this paper, we propose a zero-shot personalized Lip2speech synthesis method, in which face images control speaker identities. A variational autoencoder is adopted to disentangle the speaker identity and linguistic content representations, which enables speaker embeddings to control the voice characteristics of synthetic speech for unseen speakers. Furthermore, we propose associated cross-modal representation learning to promote the ability of face-based speaker embeddings (FSE) on voice control. Extensive experiments verify the effectiveness of the proposed method whose synthetic utterances are more natural and matching with the personality of input video than the compared methods. To our best knowledge, this paper makes the first attempt on zero-shot personalized Lip2speech synthesis with a face image rather than reference audio to control voice characteristics. © 2023 IEEE.

关键词： speech synthesis

来源：评论

学校读者我要写书评

暂无评论

speech Reconstruction from Silent Tongue and Lip Articulation by Pseudo Target Generation and Domain Adversarial Training 48

Speech Reconstruction from Silent Tongue and Lip Articulatio...

引用

48th IEEE International Conference on Acoustics, speech and Signal processing, ICASSP 2023

作者： Zheng, Rui-Chen Ai, Yang Ling, Zhen-Hua University of Science and Technology of China National Engineering Research Center of Speech and Language Information Processing Hefei China

ISBN: (纸本)9781728163277

This paper studies the task of speech reconstruction from ultrasound tongue images and optical lip videos recorded in a silent speaking mode, where people only activate their intra-oral and extra-oral articulators without producing sound. This task falls under the umbrella of articulatory-to-acoustic conversion, and may also be refered to as a silent speech interface. We propose to employ a method built on pseudo target generation and domain adversarial training with an iterative training strategy to improve the intelligibility and naturalness of the speech recovered from silent tongue and lip articulation. Experiments show that our proposed method significantly improves the intelligibility and naturalness of the reconstructed speech in silent speaking mode compared to the baseline TaLNet model. When using an automatic speech recognition (ASR) model to measure intelligibility, the word error rate (WER) of our proposed method decreases by over 15% compared to the baseline. In addition, our proposed method also outperforms the baseline on the intelligibility of the speech reconstructed in vocalized articulating mode, reducing the WER by approximately 10%. © 2023 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Neural speech Phase Prediction Based on Parallel Estimation Architecture and Anti-Wrapping Losses 48

Neural Speech Phase Prediction Based on Parallel Estimation ...

引用

48th IEEE International Conference on Acoustics, speech and Signal processing, ICASSP 2023

作者： Ai, Yang Ling, Zhen-Hua University of Science and Technology of China National Engineering Research Center of Speech and Language Information Processing Hefei China

ISBN: (纸本)9781728163277

This paper presents a novel speech phase prediction model which predicts wrapped phase spectra directly from amplitude spectra by neural networks. The proposed model is a cascade of a residual convolutional network and a parallel estimation architecture. The parallel estimation architecture is composed of two parallel linear convolutional layers and a phase calculation formula, imitating the process of calculating the phase spectra from the real and imaginary parts of complex spectra and strictly restricting the predicted phase values to the principal value interval. To avoid the error expansion issue caused by phase wrapping, we design anti-wrapping training losses defined between the predicted wrapped phase spectra and natural ones by activating the instantaneous phase error, group delay error and instantaneous angular frequency error using an anti-wrapping function. Experimental results show that our proposed neural speech phase prediction model outperforms the iterative Griffin-Lim algorithm and other neural network-based method, in terms of both reconstructed speech quality and generation speed. © 2023 IEEE.

关键词： Group delay

来源：评论

学校读者我要写书评

暂无评论

Merging Feed-Forward Sublayers for Compressed Transformers

arXiv

引用

arXiv 2025年

作者： Verma, Neha Murray, Kenton Duh, Kevin Center for Language and Speech Processing United States Human Language Technology Center Excellence Johns Hopkins University United States

With the ubiquity of large deep learning models and their growing number of use cases, the need for high-quality compression techniques is growing in order to deploy these models widely across diverse hardware and memory settings. In this work, we present a novel approach to model compression by merging parameter groups within a model, rather than pruning away less important parameters. Specifically, we select, align, and merge separate feed-forward sublayers in Transformer models, and test our method on language modeling, image classification, and machine translation. With our method, we demonstrate performance comparable to the original models while combining more than a third of model feed-forward sublayers, and demonstrate improved performance over a strong layer-pruning baseline. For instance, we can remove over 21% of total parameters from a vision transformer, while maintaining 99% of its original performance. Additionally, we observe that some groups of feed-forward sublayers exhibit high activation similarity, which may help explain their surprising mergeability. Copyright © 2025, The Authors. All rights reserved.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Clustering Unsupervised Representations as Defense Against Poisoning Attacks on speech Commands Classification System

Clustering Unsupervised Representations as Defense Against P...

引用

2023 IEEE Automatic speech Recognition and Understanding Workshop, ASRU 2023

作者： Thebaud, Thomas Joshi, Sonal Li, Henry Sustek, Martin Villalba, Jesus Khudanpur, Sanjeev Dehak, Najim Johns Hopkins University Center for Language and Speech Processing United States Brno University of Technology Faculty of Information Technology Czech Republic

ISBN: (纸本)9798350306897

Poisoning attacks entail attackers intentionally tampering with training data. In this paper, we consider a dirty-label poisoning attack scenario on a speech commands classification system. The threat model assumes that certain utterances from one of the classes (source class) are poisoned by superimposing a trigger on it, and its label is changed to another class selected by the attacker (target class). We propose a filtering defense against such an attack. First, we use DIstillation with NO labels (DINO) to learn unsupervised representations for all the training examples. Next, we use K-means and LDA to cluster these representations. Finally, we keep the utterances with the most repeated label in their cluster for training and discard the rest. For a 10% poisoned source class, we demonstrate a drop in attack success rate from 99.75% to 0.25%. We test our defense against a variety of threat models, including different target and source classes, as well as trigger variations. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

The USTC System for EEG-Music Emotion Recognition Challenge

The USTC System for EEG-Music Emotion Recognition Challenge

引用

2025 IEEE International Conference on Acoustics, speech, and Signal processing, ICASSP 2025

作者： Chen, Jiaxin Wang, Yiming Liu, Yin-Long Feng, Rui Yuan, Jiahong Ling, Zhen-Hua National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China Hefei China Interdisciplinary Research Center for Linguistic Sciences University of Science and Technology of China Hefei China

ISBN: (纸本)9798350368741

This paper presents the Neural Harmony team's submission to Task 1 (Person Identification) of the ICASSP 2025 EEG-Music Emotion Recognition Challenge, which aims to identify the subject from a given EEG segment. To enhance performance, we propose a novel architecture incorporating the Multiscale ConvBlock and integrating attention mechanisms with convolutional networks. We also reprocessed the data and trained multiple models with different train-validation splits, which were ensembled during testing to further improve robustness. Our final results on the test data exceed the challenge baseline, achieving 100% accuracy in Person Identification. Additionally, unseen subjects were introduced to evaluate the model's generalization ability, and the results confirm the model's strong adaptability to new subjects. © 2025 IEEE.

关键词： attention convolutional network EEG Person Identification

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：