Zhaocheng Huang

Zhaocheng Huang

Auto-generated profile, based on publicly available information

Zhaocheng Huang

School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, NSW, Australia

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 October 2019 in IEEE Journal of Selected Topics in Signal Processing
Verified
Journal Article
Closed access
ZHZhaocheng Huang
Zhaocheng Huang
JEJulien Epps
Julien Epps
DJDale Joachim
Dale Joachim
VSVidhyasaharan Sethu
Vidhyasaharan Sethu
The processing of speech as an explicit sequence of events is common in automatic speech recognition (linguistic events), but has received relatively little attention in paralinguistic speech classification despite its potential for characterizing broad acoustic event sequences. This paper proposes a framework for analyzing speech as a sequence of acoustic events, and investigates its application to depression detection. In this framework, acoustic space regions are tokenized to `words' representing speech events at fixed or irregular intervals. This tokenization allows the exploitation of acoustic word features using proven natural language processing methods. A key advantage of this framework is its ability to accommodate heterogeneous event types: herein we combine acoustic words and speech landmarks, which are articulation-related speech events. Another advantage is the option to fuse such heterogeneous events at various levels, including the embedding level. Evaluation of the proposed framework on both controlled laboratory-grade supervised audio recordings as well as unsupervised self-administered smartphone recordings highlight the merits of the proposed framework across both datasets, with the proposed landmark-dependent acoustic words achieving improvements in F1(depressed) of up to 15% and 13% for SH2-FS and DAIC-WOZ respectively, relative to acoustic speech baseline approaches.

7 October 2019 in IEEE Transactions on Affective Computing
Verified
Journal Article
Closed access
ZHZhaocheng Huang
Zhaocheng Huang
JEJulien Epps
Julien Epps
DJDale Joachim
Dale Joachim
The massive and growing burden imposed on modern society by depression has motivated investigations into early detection through automated, scalable and non-invasive methods, including those based on speech. However, speech-based methods that capture articulatory information effectively across different recording devices and in naturalistic environments are still needed. This article proposes two feature sets associated with speech articulation events based on counts and durations of sequential landmark groups or n-grams. Statistical analysis of the duration-based features reveals that durations from several consecutive landmark bigrams and onset-offset landmark pairs are significant in discriminating depressed from non-depressed speakers. In addition to investigating different normalization approaches and values of n for landmark n-gram features, experiments across different elicitation tasks suggest that the features can be tailored to capture different articulatory aspects of depressed voices. Evaluations of both landmark duration features and landmark n-gram features on the DAIC-WOZ and SH2 datasets show that they are highly effective, either alone or fused, relative to existing approaches.

11 March 2021 in Journal of Healthcare Informatics Research
Verified
Journal Article
Closed access
PDF file
BSBrian Stasak
Brian Stasak
ZHZhaocheng Huang
Zhaocheng Huang
SRSabah Razavi
Sabah Razavi
DJDale Joachim
Dale Joachim
JEJulien Epps
Julien Epps

4 April 2018 in IEEE Transactions on Affective Computing
Verified
Journal Article
Closed access
ZHZhaocheng Huang
Zhaocheng Huang
JEJulien Epps
Julien Epps
Phonetic variability has long been considered a confounding factor for emotional speech processing, so phonetic features have been rarely explored. However, surprisingly some features with purely phonetic information have shown state-of-the-art performance for continuous prediction of emotions (e.g. arousal and valence), for which the underlying causes are unknown to date. In this article, we present in-depth investigations into phonetic features on three widely used corpora: RECOLA, SEMAINE and USC CreativeIT to explore this from two perspectives: acoustic space partitioning information and phonetic content. First, comparisons of multiple different partitioning methods confirm the significance of partitioning information in speech, and reveal the new understanding that varying the number of partitions has a greater effect on valence than arousal prediction: a detailed representation of the acoustic space is needed for valence, whilst a general one is adequate for arousal. Second, phoneme-specific examination of phonetic features suggests that phonetic content is less emotionally informative than partitioning information, and is more important for arousal than for valence. Furthermore, we propose a novel set of phonetically-aware acoustic features, attaining significant improvements for valence (in particular) and arousal prediction across RECOLA, SEMAINE and CreativeIT, compared with conventional reference acoustic features.

5 June 2018 in Frontiers in ICT
Verified
Journal Article
Open access
PDF file
ZHZhaocheng Huang
Zhaocheng Huang
JEJulien Epps
Julien Epps
The fact that emotions are dynamic in nature and evolve across time has been explored relatively less often in automatic emotion recognition systems to date. Although within-utterance information about emotion changes recently has received some attention, there remain open questions unresolved, such as how to approach delta emotion ground truth, how to predict the extent of emotion change from speech, and how well change can be predicted relative to absolute emotion ratings. In this article, we investigate speech-based automatic systems for continuous prediction of the extent of emotion changes in arousal/valence. We propose the use of regression (smoothed) deltas as ground truth for emotion change, which yielded considerably higher inter-rater reliability than first-order deltas, a commonly used approach in previous research, and represent a more appropriate approach to derive annotations for emotion change research, findings which are applicable beyond speech-based systems. In addition, the first system design for continuous emotion change prediction from speech is explored. Experimental results under the Output-Associative Relevance Vector Machine framework interestingly show that changes in emotion ratings may be better predicted than absolute emotion ratings on the RECOLA database, achieving 0.74 vs. 0.71 for arousal and 0.41 vs. 0.37 for valence in concordance correlation coefficients. However, further work is needed to achieve effective emotion change prediction performances on the SEMAINE database, due to the large number of non-change frames in the absolute emotion ratings.

1 November 2021 in Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Verified
Conference Paper
Open access
BSBrian Stasak
Brian Stasak
ZHZhaocheng Huang
Zhaocheng Huang
JEJulien Epps
Julien Epps
DJDale Joachim
Dale Joachim
While the psychological Stroop color test has frequently been used to analyze response delays in temporal cognitive processing, minimal research has examined incorrect/correct verbal test response pattern differences exhibited in healthy control and clinically depressed populations. Further, the development of speech error features with an emphasis on sequential Stroop test responses has been unexplored for automatic depression classification. In this study which uses speech recorded via a smart device, an analysis of и-gram error sequence distributions shows that participants with clinical depression produce more Stroop color test errors, especially sequential errors, than the healthy controls. By utilizing и-gram error features derived from multisession manual transcripts, experimentation shows that trigram error features generate up to 95% depression classification accuracy, whereas an acoustic feature baseline achieve only upwards of 75%. Moreover, и-gram error features using ASR transcripts produced up to 90% depression classification accuracy.