English
Related papers

Related papers: From Coarse to Fine: Efficient Training for Audio …

200 papers

Self-supervised pre-training of a speech foundation model, followed by supervised fine-tuning, has shown impressive quality improvements on automatic speech recognition (ASR) tasks. Fine-tuning separate foundation models for many downstream…

Machine Learning · Computer Science 2022-11-08 Zhouyuan Huo , Khe Chai Sim , Bo Li , Dongseong Hwang , Tara N. Sainath , Trevor Strohman

The remarkable success of Large Language Models (LLMs) relies heavily on their substantial scale, which poses significant challenges during model deployment in terms of latency and memory consumption. Recently, numerous studies have…

Computation and Language · Computer Science 2024-12-19 Weiyu Huang , Yuezhou Hu , Guohao Jian , Jun Zhu , Jianfei Chen

We present STFTCodec, a novel spectral-based neural audio codec that efficiently compresses audio using Short-Time Fourier Transform (STFT). Unlike waveform-based approaches that require large model capacity and substantial memory…

Sound · Computer Science 2025-03-24 Tao Feng , Zhiyuan Zhao , Yifan Xie , Yuqi Ye , Xiangyang Luo , Xun Guan , Yu Li

The audio-visual speech fusion strategy AV Align has shown significant performance improvements in audio-visual speech recognition (AVSR) on the challenging LRS2 dataset. Performance improvements range between 7% and 30% depending on the…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-20 George Sterpu , Christian Saam , Naomi Harte

Convolutional layers with 1-D filters are often used as frontend to encode audio signals. Unlike fixed time-frequency representations, they can adapt to the local characteristics of input data. However, 1-D filters on raw audio are hard to…

Sound · Computer Science 2024-09-02 Daniel Haider , Felix Perfler , Vincent Lostanlen , Martin Ehler , Peter Balazs

Foundation models achieve state-of-the-art performance across different tasks, but their size and computational demands raise concerns about accessibility and sustainability. Existing efficiency methods often require additional retraining…

We consider the problem of detecting, isolating and classifying elephant calls in continuously recorded audio. Such automatic call characterisation can assist conservation efforts and inform environmental management strategies. In contrast…

Sound · Computer Science 2025-04-03 Christiaan M. Geldenhuys , Thomas R. Niesler

Vision Transformers (ViTs) have achieved state-of-the-art performance across various computer vision tasks, but their high computational cost remains a challenge. Token pruning has been proposed to reduce this cost by selectively removing…

Sound · Computer Science 2025-10-27 Taehan Lee , Hyukjun Lee

End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the…

Artificial Intelligence · Computer Science 2021-03-19 Md Akmal Haidar , Chao Xing , Mehdi Rezagholizadeh

Previous work has shown that for low-resource source languages, automatic speech-to-text translation (AST) can be improved by pretraining an end-to-end model on automatic speech recognition (ASR) data from a high-resource language. However,…

Computation and Language · Computer Science 2020-02-11 Mihaela C. Stoian , Sameer Bansal , Sharon Goldwater

How to visually localize multiple sound sources in unconstrained videos is a formidable problem, especially when lack of the pairwise sound-object annotations. To solve this problem, we develop a two-stage audiovisual learning framework…

Computer Vision and Pattern Recognition · Computer Science 2020-07-15 Rui Qian , Di Hu , Heinrich Dinkel , Mengyue Wu , Ning Xu , Weiyao Lin

While significant improvements have been made in recent years in terms of end-to-end automatic speech recognition (ASR) performance, such improvements were obtained through the use of very large neural networks, unfit for embedded use on…

Computation and Language · Computer Science 2020-03-25 Alex Bie , Bharat Venkitesh , Joao Monteiro , Md. Akmal Haidar , Mehdi Rezagholizadeh

Conformers have shown great results in speech processing due to their ability to capture both local and global interactions. In this work, we utilize a self-supervised contrastive learning framework to train conformer-based encoders that…

Sound · Computer Science 2025-09-12 Kemal Altwlkany , Elmedin Selmanovic , Sead Delalic

Automatic speech recognition (ASR) has reached a level of accuracy in recent years, that even outperforms humans in transcribing speech to text. Nevertheless, all current ASR approaches show a certain weakness against ambient noise. To…

Sound · Computer Science 2023-12-22 Christopher Simic , Tobias Bocklet

While transformers demonstrate outstanding performance across various audio tasks, their application to neural vocoders remains challenging. Neural vocoders require the generation of long audio signals at the sample level, which demands…

Sound · Computer Science 2025-12-30 Seongho Hong , Yong-Hoon Choi

Many neural speech enhancement and source separation systems operate in the time-frequency domain. Such models often benefit from making their Short-Time Fourier Transform (STFT) front-ends trainable. In current literature, these are…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-24 Jonah Casebeer , Umut Isik , Shrikant Venkataramani , Arvindh Krishnaswamy

Neural front-ends are an appealing alternative to traditional, fixed feature extraction pipelines for automatic speech recognition (ASR) systems since they can be directly trained to fit the acoustic model. However, their performance often…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-01 Peter Vieting , Maximilian Kannen , Benedikt Hilmes , Ralf Schlüter , Hermann Ney

In this paper, we propose the coarse-to-fine optimization for the task of speech enhancement. Cosine similarity loss [1] has proven to be an effective metric to measure similarity of speech signals. However, due to the large variance of the…

Sound · Computer Science 2019-08-23 Jian Yao , Ahmad Al-Dahle

Most audio processing pipelines involve transformations that act on fixed-dimensional input representations of audio. For example, when using the Short Time Fourier Transform (STFT) the DFT size specifies a fixed dimension for the input…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-28 Krishna Subramani , Paris Smaragdis

This paper investigates a novel approach to end-to-end speech translation (ST) based on aligning frozen pre-trained automatic speech recognition (ASR) and machine translation (MT) models via a small connector module (Q-Former, our…

Computation and Language · Computer Science 2024-11-28 Šimon Sedláček , Santosh Kesiraju , Alexander Polok , Jan Černocký