English
Related papers

Related papers: Selective Augmentation: Improving Universal Automa…

200 papers

Whisper's robust performance in automatic speech recognition (ASR) is often attributed to its massive 680k-hour training set, an impractical scale for most researchers. In this work, we examine how linguistic and acoustic diversity in…

Computation and Language · Computer Science 2025-05-28 Dancheng Liu , Amir Nassereldine , Chenhui Xu , Jinjun Xiong

Recent work has shown the feasibility and benefit of bootstrapping an integrated sequence-to-sequence (Seq2Seq) linguistic frontend from a traditional pipeline-based frontend for text-to-speech (TTS). To overcome the fixed lexical coverage…

Computation and Language · Computer Science 2024-09-17 Siqi Sun , Korin Richmond

We propose a novel prompt tuning method called CoAPT(Context Attribute words in Prompt Tuning) for few/zero-shot image classification. The core motivation is that attributes are descriptive words with rich information about a given concept.…

Computer Vision and Pattern Recognition · Computer Science 2024-07-22 Gun Lee , Subin An , Sungyong Baik , Soochahn Lee

Despite significant advances in recent years, the existing Computer-Assisted Pronunciation Training (CAPT) methods detect pronunciation errors with a relatively low accuracy (precision of 60% at 40%-80% recall). This Ph.D. work proposes…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-15 Daniel Korzekwa

Quality of data plays an important role in most deep learning tasks. In the speech community, transcription of speech recording is indispensable. Since the transcription is usually generated artificially, automatically finding errors in…

Computation and Language · Computer Science 2019-07-23 Xiaofei Wang , Jinyi Yang , Ruizhi Li , Samik Sadhu , Hynek Hermansky

Prompt-based fine-tuning has boosted the performance of Pre-trained Language Models (PLMs) on few-shot text classification by employing task-specific prompts. Yet, PLMs are unfamiliar with prompt-style expressions during pre-training, which…

Computation and Language · Computer Science 2022-05-12 Jianing Wang , Chengyu Wang , Fuli Luo , Chuanqi Tan , Minghui Qiu , Fei Yang , Qiuhui Shi , Songfang Huang , Ming Gao

In this paper, we aim to unveil the impact of data augmentation in audio-language multi-modal learning, which has not been explored despite its importance. We explore various augmentation methods at not only train-time but also test-time…

Sound · Computer Science 2023-05-24 Eungbeom Kim , Jinhee Kim , Yoori Oh , Kyungsu Kim , Minju Park , Jaeheon Sim , Jinwoo Lee , Kyogu Lee

Data augmentation has proven widely effective in computer vision. In Natural Language Processing (NLP) data augmentation remains an area of active research. There is no widely accepted augmentation technique that works well across tasks and…

Computation and Language · Computer Science 2023-03-07 Isabel Garcia Pietri , Kineret Stanley

Retrieval-augmented language models can better adapt to changes in world state and incorporate long-tail knowledge. However, most existing methods retrieve only short contiguous chunks from a retrieval corpus, limiting holistic…

Computation and Language · Computer Science 2024-02-01 Parth Sarthi , Salman Abdullah , Aditi Tuli , Shubh Khanna , Anna Goldie , Christopher D. Manning

We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner. Inspired by recent contrastive self-supervised learning algorithms used for image and NLP pretraining,…

Computation and Language · Computer Science 2021-03-29 Dongsheng Luo , Wei Cheng , Jingchao Ni , Wenchao Yu , Xuchao Zhang , Bo Zong , Yanchi Liu , Zhengzhang Chen , Dongjin Song , Haifeng Chen , Xiang 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

Bootstrapping speech recognition on limited data resources has been an area of active research for long. The recent transition to all-neural models and end-to-end (E2E) training brought along particular challenges as these models are known…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-21 Manuel Giollo , Deniz Gunceler , Yulan Liu , Daniel Willett

Multi-hop questions still stump large language models (LLMs), which struggle to link information across multiple reasoning steps. We introduce Auto-Patch, a novel method that dynamically patches hidden states during inference to enhance…

Computation and Language · Computer Science 2025-06-03 Aviv Jan , Dean Tahory , Omer Talmi , Omar Abo Mokh

We consider the problem of data augmentation, i.e., generating artificial samples to extend a given corpus of training data. Specifically, we propose attributed-guided augmentation (AGA) which learns a mapping that allows to synthesize data…

Computer Vision and Pattern Recognition · Computer Science 2017-08-29 Mandar Dixit , Roland Kwitt , Marc Niethammer , Nuno Vasconcelos

Recent advancements in AI have democratized its deployment as a healthcare assistant. While pretrained models from large-scale visual and audio datasets have demonstrably generalized to this task, surprisingly, no studies have explored…

Sound · Computer Science 2024-05-07 June-Woo Kim , Miika Toikkanen , Sangmin Bae , Minseok Kim , Ho-Young Jung

Many studies combine text and audio to capture multi-modal information but they overlook the model's generalization ability on new datasets. Introducing new datasets may affect the feature space of the original dataset, leading to…

Sound · Computer Science 2025-07-29 Yingfei Sun , Xu Gu , Wei Ji , Hanbin Zhao , Yifang Yin , Roger Zimmermann

End-to-end speech translation relies on data that pair source-language speech inputs with corresponding translations into a target language. Such data are notoriously scarce, making synthetic data augmentation by back-translation or…

Computation and Language · Computer Science 2023-06-12 Tsz Kin Lam , Shigehiko Schamoni , Stefan Riezler

We present a bootstrapping method to develop an annotated corpus, which is specially useful for languages with few available resources. The method is being applied to develop a corpus of Spanish of over 5Mw. The method consists on taking…

Computation and Language · Computer Science 2007-05-23 L. Marquez , L. Padro , H. Rodriguez

Recent advancements in Automatic Piano Transcription (APT) have significantly improved system performance, but the impact of noisy environments on the system performance remains largely unexplored. This study investigates the impact of…

Sound · Computer Science 2024-10-21 Yonghyun Kim , Alexander Lerch

Recent automatic lyrics transcription (ALT) approaches focus on building stronger acoustic models or in-domain language models, while the pronunciation aspect is seldom touched upon. This paper applies a novel computational analysis on the…

Information Retrieval · Computer Science 2021-06-22 Emir Demirel , Sven Ahlback , Simon Dixon