paper-with-me

Papers

Asca: less audio data is more insightful

2023-09-23 · Xiang Li, JunHao Chen, Chao Li, Hongwu Lv

Audio recognition in specialized areas such as birdsong and submarine acoustics faces challenges in large-scale pre-training due to the limitations in available samples imposed by sampling environments and specificity requirements. While the Transformer model excels in audio recognition, its dependence on vast amounts of data becomes restrictive in resource-limited settings. Addressing this, we introduce the Audio Spectrogram Convolution Attention (ASCA) based on CoAtNet, integrating a Transformer-convolution hybrid architecture, novel network design, and attention techniques, further augmented with data enhancement and regularization strategies. On the BirdCLEF2023 and AudioSet(Balanced), ASCA achieved accuracies of 81.2% and 35.1%, respectively, significantly outperforming competing methods. The unique structure of our model enriches output, enabling generalization across various audio detection tasks. Our code can be found at https://github.com/LeeCiang/ASCA.

📄 PDF Abstract BibTeX arXiv:2309.13373

Code (1)

leeciang/asca 공식 구현

Tasks

Specificity

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Cascaded Composite Turbulence and Misalignment: Statistical Characterization and Applications to Reconfigurable Intelligent Surface-Empowered Wireless Systems

2021-06-29 · Alexandros-Apostolos A. Boulogeorgos, Nestor Chatzidiamantis, Harilaos G. Sandalidis, Angeliki Alexiou 외

Reconfigurable intelligent surfaces (RISs) empowered high-frequency (HF) wireless systems are expected to become the supporting pillar for several reliability and data rate hungry applications. Such systems are, however,…

Unified Audio Intelligence Without Regressing on Text Intelligence

2026-07-06 · Zhifeng Kong, Sang-gil Lee, Jaehyeon Kim, Boxin Wang 외 arxiv

Audio intelligence involves understanding, reasoning about, and generating both audio and speech. In this work, we introduce Nemotron-Labs-Audex-30B-A3B (Audex), a unified audio-text LLM built on Nemotron-Cascade-2-30B-A…

multimodal generationSpeech RecognitionAudio Generation

Audio Super-Resolution with Latent Bridge Models

2025-09-22 · Chang Li, Zehua Chen, Liyuan Wang, Jun Zhu arxiv

Audio super-resolution (SR), i.e., upsampling the low-resolution (LR) waveform to the high-resolution (HR) version, has recently been explored with diffusion and bridge models, while previous methods often suffer from su…

Audio Super-Resolution

Generative Spoken Dialogue Language Modeling

2022-03-30 · Tu Anh Nguyen, Eugene Kharitonov, Jade Copet, Yossi Adi 외

We introduce dGSLM, the first "textless" model able to generate audio samples of naturalistic spoken dialogues. It uses recent work on unsupervised spoken unit discovery coupled with a dual-tower transformer architecture…

Language ModelingLanguage Modelling

ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systems

2025-03-11 · Siddhant Arora, Yifan Peng, Jiatong Shi, Jinchuan Tian 외

Advancements in audio foundation models (FMs) have fueled interest in end-to-end (E2E) spoken dialogue systems, but different web interfaces for each system makes it challenging to compare and contrast them effectively. …

DiversitySpoken Dialogue Systems