English
Related papers

Related papers: PAT: Parameter-Free Audio-Text Aligner to Boost Ze…

200 papers

Automatic speech recognition (ASR) models rely on high-quality transcribed data for effective training. Generating pseudo-labels for large unlabeled audio datasets often relies on complex pipelines that combine multiple ASR outputs through…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-06 Jeena Prakash , Blessingh Kumar , Kadri Hacioglu , Bidisha Sharma , Sindhuja Gopalan , Malolan Chetlur , Shankar Venkatesan , Andreas Stolcke

Recent advances in automatic speech recognition (ASR) and speech enhancement have led to a widespread assumption that improving perceptual audio quality should directly benefit recognition accuracy. In this work, we rigorously examine…

Sound · Computer Science 2026-03-06 Akif Islam , Raufun Nahar , Md. Ekramul Hamid

Manual annotation of audio datasets is labour intensive, and it is challenging to balance label granularity with acoustic separability. We introduce AuditoryHuM, a novel framework for the unsupervised discovery and clustering of auditory…

Sound · Computer Science 2026-02-24 Henry Zhong , Jörg M. Buchholz , Julian Maclaren , Simon Carlile , Richard F. Lyon

A wide range of NLP tasks benefit from the fine-tuning of pretrained language models (PLMs). However, a number of redundant parameters which contribute less to the downstream task are observed in a directly fine-tuned model. We consider the…

Computation and Language · Computer Science 2022-10-26 Yupeng Zhang , Hongzhi Zhang , Sirui Wang , Wei Wu , Zhoujun Li

A hybrid autoregressive transducer (HAT) is a variant of neural transducer that models blank and non-blank posterior distributions separately. In this paper, we propose a novel internal acoustic model (IAM) training strategy to enhance…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-01 Takafumi Moriya , Takanori Ashihara , Masato Mimura , Hiroshi Sato , Kohei Matsuura , Ryo Masumura , Taichi Asami

Recent advances in large-scale vision and language models have led to significant progress in zero-shot learning tasks. Methods such as CoOp and CoCoOp have shown that replacing handcrafted prompts with learnable vectors, known as prompt…

Computer Vision and Pattern Recognition · Computer Science 2025-11-06 Gahyeon Kim , Sohee Kim , Seokju Lee

For self-supervised speech processing, it is crucial to use pretrained models as speech representation extractors. In recent works, increasing the size of the model has been utilized in acoustic model training in order to achieve better…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-04 Po-Han Chi , Pei-Hung Chung , Tsung-Han Wu , Chun-Cheng Hsieh , Yen-Hao Chen , Shang-Wen Li , Hung-yi Lee

Large language models (LLMs) are increasingly integrated with specialized external tools, yet many tasks demand zero-shot tool usage with minimal or noisy documentation. Existing solutions rely on manual rewriting or labeled data for…

Computation and Language · Computer Science 2025-06-13 Wei Fang , Yang Zhang , Kaizhi Qian , James Glass , Yada Zhu

Zero-shot text-to-speech (TTS) synthesis aims to clone any unseen speaker's voice without adaptation parameters. By quantizing speech waveform into discrete acoustic tokens and modeling these tokens with the language model, recent language…

Fine-tuning large language models (LLMs) often causes overfitting to specific prompt wording, where minor phrasing variations drastically reduce performance. To address this, we propose Prompt-Agnostic Fine-Tuning (PAFT), a method that…

Computation and Language · Computer Science 2025-10-20 Chenxing Wei , Yao Shu , Mingwen Ou , Ying Tiffany He , Fei Richard Yu

We propose a simple method for automatic speech recognition (ASR) by fine-tuning BERT, which is a language model (LM) trained on large-scale unlabeled text data and can generate rich contextual representations. Our assumption is that given…

Sound · Computer Science 2021-02-02 Wen-Chin Huang , Chia-Hua Wu , Shang-Bao Luo , Kuan-Yu Chen , Hsin-Min Wang , Tomoki Toda

Speech emotion recognition (SER) has drawn increasing attention for its applications in human-machine interaction. However, existing SER methods ignore the information gap between the pre-training speech recognition task and the downstream…

Sound · Computer Science 2023-10-03 Dongyuan Li , Yusong Wang , Kotaro Funakoshi , Manabu Okumura

Advances in speech representation and large language models have enhanced zero-shot text-to-speech (TTS) performance. However, existing zero-shot TTS models face challenges in capturing the complex correlations between acoustic and semantic…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-29 Jingyuan Xing , Zhipeng Li , Jialong Mai , Xiaofen Xing , Xiangmin Xu

Language models built using semi-supervised machine learning on large corpora of natural language have very quickly enveloped the fields of natural language generation and understanding. In this paper we apply a zero-shot approach…

Computation and Language · Computer Science 2022-01-25 Darren Abramson , Ali Emami

Dynamic parameterization of acoustic environments has drawn widespread attention in the field of audio processing. Precise representation of local room acoustic characteristics is crucial when designing audio filters for various audio…

Audio and Speech Processing · Electrical Eng. & Systems 2024-04-26 Chunxi Wang , Maoshen Jia , Meiran Li , Changchun Bao , Wenyu Jin

The integration of prompt tuning with multimodal learning has shown significant generalization abilities for various downstream tasks. Despite advancements, existing methods heavily depend on massive modality-specific labeled data (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-11 Xiangyu Wu , Feng Yu , Yang Yang , Jianfeng Lu

While Large Language Models (LLMs) have achieved tremendous success in various applications, they are also susceptible to jailbreaking attacks. Several primary defense strategies have been proposed to protect LLMs from producing harmful…

Machine Learning · Computer Science 2024-11-01 Yichuan Mo , Yuji Wang , Zeming Wei , Yisen Wang

Recently, neural networks based purely on self-attention, such as the Vision Transformer (ViT), have been shown to outperform deep learning models constructed with convolutional neural networks (CNNs) on various vision tasks, thus extending…

Sound · Computer Science 2022-02-14 Yuan Gong , Cheng-I Jeff Lai , Yu-An Chung , James Glass

With the success of pre-trained visual-language (VL) models such as CLIP in visual representation tasks, transferring pre-trained models to downstream tasks has become a crucial paradigm. Recently, the prompt tuning paradigm, which draws…

Computer Vision and Pattern Recognition · Computer Science 2023-12-14 Jingsheng Gao , Jiacheng Ruan , Suncheng Xiang , Zefang Yu , Ke Ji , Mingye Xie , Ting Liu , Yuzhuo Fu

Large Audio-Language Models (LALMs) are often constrained by short audio context windows, even when their text backbones support long contexts, limiting long-form audio understanding. Prior work has introduced context-extension methods…

Computation and Language · Computer Science 2026-01-22 Yuatyong Chaichana , Pittawat Taveekitworachai , Warit Sirichotedumrong , Potsawee Manakul , Kunat Pipatanakul