159 citations · 402 across the 20 of their papers we have counts for
13 papers · 1 filter
Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition
Zhifu Gao, Shiliang Zhang, Ian McLoughlin +1
Transformers have recently dominated the ASR field. Although able to yield good performance, they involve an autoregressive (AR) decoder to generate tokens one by one, which is com…
An Ensemble of Deep Learning Frameworks Applied For Predicting Respiratory Anomalies
Lam Pham, Dat Ngo, Truong Hoang +2
In this paper, we evaluate various deep learning frameworks for detecting respiratory anomalies from input audio recordings. To this end, we firstly transform audio respiratory cyc…
Extremely Low Footprint End-to-End ASR System for Smart Device
Zhifu Gao, Yiwu Yao, Shiliang Zhang +3
Recently, end-to-end (E2E) speech recognition has become popular, since it can integrate the acoustic, pronunciation and language models into a single neural network, which outperf…
Multi-view Audio and Music Classification
Huy Phan, Huy Le Nguyen, Oliver Y. Chén +4
We propose in this work a multi-view learning approach for audio and music classification. Considering four typical low-level representations (i.e. different views) commonly used f…
Universal ASR: Unifying Streaming and Non-Streaming ASR Using a Single Encoder-Decoder Model
Zhifu Gao, Shiliang Zhang, Ming Lei +1
Recently, online end-to-end ASR has gained increasing attention. However, the performance of online systems still lags far behind that of offline systems, with a large gap in quali…
Self-Attention Generative Adversarial Network for Speech Enhancement
Huy Phan, Huy Le Nguyen, Oliver Y. Chén +4
Existing generative adversarial networks (GANs) for speech enhancement solely rely on the convolution operation, which may obscure temporal dependencies across the sequence input.…
SAN-M: Memory Equipped Self-Attention for End-to-End Speech Recognition
Zhifu Gao, Shiliang Zhang, Ming Lei +1
End-to-end speech recognition has become popular in recent years, since it can integrate the acoustic, pronunciation and language models into a single neural network. Among end-to-…
Robust Acoustic Scene Classification using a Multi-Spectrogram Encoder-Decoder Framework
Lam Pham, Huy Phan, Truc Nguyen +3
This article proposes an encoder-decoder network model for Acoustic Scene Classification (ASC), the task of identifying the scene of an audio recording from its acoustic signature.…
Robust Deep Learning Framework For Predicting Respiratory Anomalies and Diseases
Lam Pham, Ian McLoughlin, Huy Phan +3
This paper presents a robust deep learning framework developed to detect respiratory diseases from recordings of respiratory sounds. The complete detection process firstly involves…
Spatio-Temporal Attention Pooling for Audio Scene Classification
Huy Phan, Oliver Y. Chén, Lam Pham +4
Acoustic scenes are rich and redundant in their content. In this work, we present a spatio-temporal attention pooling layer coupled with a convolutional recurrent neural network to…
Beyond Equal-Length Snippets: How Long is Sufficient to Recognize an Audio Scene?
Huy Phan, Oliver Y. Chén, Philipp Koch +4
Due to the variability in characteristics of audio scenes, some scenes can naturally be recognized earlier than others. In this work, rather than using equal-length snippets for al…
Enabling Early Audio Event Detection with Neural Networks
Huy Phan, Philipp Koch, Ian McLoughlin +1
This paper presents a methodology for early detection of audio events from audio streams. Early detection is the ability to infer an ongoing event during its initial stage. The pro…
Learning Compact Structural Representations for Audio Events Using Regressor Banks
Huy Phan, Marco Maass, Lars Hertel +3
We introduce a new learned descriptor for audio signals which is efficient for event representation. The entries of the descriptor are produced by evaluating a set of regressors on…