Search Results - "Biqiao Zhang"
-
1
Cross-corpus acoustic emotion recognition from singing and speaking: A multi-task learning approach
Published in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01-03-2016)“…Emotion is expressed over both speech and song. Previous works have found that although spoken and sung emotion recognition are different tasks, they are…”
Get full text
Conference Proceeding Journal Article -
2
Recognizing emotion from singing and speaking using shared models
Published in 2015 International Conference on Affective Computing and Intelligent Interaction (ACII) (01-09-2015)“…Speech and song are two types of vocal communications that are closely related to each other. While significant progress has been made in both speech and music…”
Get full text
Conference Proceeding Journal Article -
3
Cross-Corpus Acoustic Emotion Recognition with Multi-Task Learning: Seeking Common Ground While Preserving Differences
Published in IEEE transactions on affective computing (01-01-2019)“…There is growing interest in emotion recognition due to its potential in many applications. However, a pervasive challenge is the presence of data variability…”
Get full text
Journal Article -
4
Exploiting Acoustic and Lexical Properties of Phonemes to Recognize Valence from Speech
Published in ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01-05-2019)“…Emotions modulate speech acoustics as well as language. The latter influences the sequences of phonemes that are produced, which in turn further modulate the…”
Get full text
Conference Proceeding -
5
Disentangled Training with Adversarial Examples for Robust Small-Footprint Keyword Spotting
Published in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (04-06-2023)“…A keyword spotting (KWS) engine continuously running on the device is exposed to various speech signals that are usually unseen beforehand. It is a challenging…”
Get full text
Conference Proceeding -
6
Spatial Attention for Far-Field Speech Recognition with Deep Beamforming Neural Networks
Published in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01-05-2020)“…In this paper, we introduce spatial attention for refining the information in multi-direction neural beamformer for far-field automatic speech recognition…”
Get full text
Conference Proceeding -
7
Effective Integration of KAN for Keyword Spotting
Published 13-09-2024“…Keyword spotting (KWS) is an important speech processing component for smart devices with voice assistance capability. In this paper, we investigate if…”
Get full text
Journal Article -
8
Query-by-Example Keyword Spotting Using Spectral-Temporal Graph Attentive Pooling and Multi-Task Learning
Published 26-08-2024“…INTERSPEECH 2024 Existing keyword spotting (KWS) systems primarily rely on predefined keyword phrases. However, the ability to recognize customized keywords is…”
Get full text
Journal Article -
9
Disentangled Training with Adversarial Examples For Robust Small-footprint Keyword Spotting
Published 23-08-2024“…ICASSP 2023 A keyword spotting (KWS) engine that is continuously running on device is exposed to various speech signals that are usually unseen before. It is a…”
Get full text
Journal Article -
10
LiCo-Net: Linearized Convolution Network for Hardware-efficient Keyword Spotting
Published 08-11-2022“…This paper proposes a hardware-efficient architecture, Linearized Convolution Network (LiCo-Net) for keyword spotting. It is optimized specifically for…”
Get full text
Journal Article -
11
Spatial Attention for Far-field Speech Recognition with Deep Beamforming Neural Networks
Published 05-11-2019“…In this paper, we introduce spatial attention for refining the information in multi-direction neural beamformer for far-field automatic speech recognition…”
Get full text
Journal Article