Voice Emotion Recognition Research Articles

Emotion recognition using machine learning: Opportunities and challenges for supporting those with autism or depression

Facial recognition technology, driven by advancements in machine learning, has become integral to various applications, from mobile security to access control. Recent developments in deep learning, particularly through convolutional and recurrent neural networks, have paved the way for enhanced emotion recognition capabilities. This paper explores the potential of facial emotion recognition (FER) and voice emotion recognition technologies, assessing their current state and future prospects. While FER techniques have evolved from traditional methods to deep learning approaches, and voice emotion recognition has shown promising results, challenges remain due to the inherent variability in human facial expressions and vocal characteristics. The paper further examines the impact of emotion recognition technologies on mental health, highlighting their potential to provide significant support to individuals with mental health disorders. By addressing the accuracy and application of these technologies, the research underscores the importance of continued innovation and careful implementation to maximize their benefits and mitigate potential risks. Ultimately, emotion recognition provides promising avenues for supporting those with mental illnesses. Aimed at fostering more personalized and effective interventions, these technologies hold the potential to revolutionize mental health care and improve the overall well-being of individuals.

No Pain, No Gain—Giving Real-Time Emotional Feedback in a Virtual Mirror Improves Collaboration in Virtual Teamwork

This study investigates the impact of real-time emotional feedback on the quality of teamwork conducted over videoconferencing. We developed a framework that provides real-time feedback through a virtual mirror based on facial and voice emotion recognition. In an experiment with 28 teams (84 participants), teams collaborated over Zoom (version 5.16.6) to set up a virtual Mars station using custom simulation software (Mars Star City, version 4.0). Participants were divided into 14 experimental teams, which were shown the virtual mirror, and 14 control teams without it. Team performance was measured by the improvement in the Mars simulation output quality. Our analysis using correlation, multi-level regression, and machine learning revealed that fewer interruptions but an increasing number over time correlated with higher performance. Higher vocal arousal and happiness also enhanced performance. We confirmed that female presence in teams boosts performance. SHAP values indicated that high variability in happiness, head movement, and positive facial valence—an “emotional rollercoaster”—positively predicted team performance. The experimental group outperformed the control group, suggesting that virtual mirroring improves virtual teamwork and that interrupting each other more while speaking less, leads to better results.

Enhancements in Immediate Speech Emotion Detection: Harnessing Prosodic and Spectral Characteristics

Speech is essential to human communication for expressing and understanding feelings. Emotional speech processing has challenges with expert data sampling, dataset organization, and computational complexity in large-scale analysis. This study aims to reduce data redundancy and high dimensionality by introducing a new speech emotion recognition system. The system employs Diffusion Map to reduce dimensionality and includes Decision Trees and K-Nearest Neighbors(KNN)ensemble classifiers. These strategies are suggested to increase voice emotion recognition accuracy. Speech emotion recognition is gaining popularity in affective computing for usage in medical, industry, and academics. This project aims to provide an efficient and robust real-time emotion identification framework. In order to identify emotions using supervised machine learning models, this work makes use of paralinguistic factors such as intensity, pitch, and MFCC. In order to classify data, experimental analysis integrates prosodic and spectral information utilizing methods like Random Forest, Multilayer Perceptron, SVM, KNN, and Gaussian Naïve Bayes. Fast training times make these machine learning models excellent for real-time applications. SVM and MLP have the highest accuracy at 70.86% and 79.52%, respectively. Comparisons to benchmarks show significant improvements over earlier models.

Family Emotional Decorative Paintings: Interaction Design for Communication

This paper describes an approach applied to decorative home paintings: an emotional interaction approach. The study utilizes the theory of constructed emotion and the Wizard of Oz research methodology to extend the user's emotional experience in home scenarios with emotional self-reflection and regulation. Family Emotion Decorative Painting uses the family-shared photo library as the image base data, obtains the emotion type through facial expression and voice emotion recognition, and correlates the moment's emotion with the emotion reacted in the picture. Through qualitative research, we found that family emotional decorative painting can bring emotional arousal and soothing to participants. Family Emotional Decorative Paintings also provoked reflection on technology in and around the home. These findings suggest several opportunities, such as designing for anticipation, better supporting reflection on the past. The study also allowed the team to question the traditional interaction design view that more frequent and prolonged human-computer interactions are a measure of good design. The team will next focus on ways for users to engage in novel and meaningful ways outside of the application.

Self-Rated Confidence in Vocal Emotion Recognition Ability: The Role of Gender.

We studied the role of gender in metacognition of voice emotion recognition ability (ERA), reflected by self-rated confidence (SRC). To this end, we guided our study in two approaches: first, by examining the role of gender in voice ERA and SRC independently and second, by looking for gender effects on the ERA association with SRC. We asked 100 participants (50 men, 50 women) to interpret a set of vocal expressions portrayed by 30 actors (16 men, 14 women) as defined by their emotional meaning. Targets were 180 repetitive lexical sentences articulated in congruent emotional voices (anger, sadness, surprise, happiness, fear) and neutral expressions. Trial by trial, the participants were assigned retrospective SRC based on their emotional recognition performance. A binomial generalized linear mixed model (GLMM) estimating ERA accuracy revealed a significant gender effect, with women encoders (speakers) yielding higher accuracy levels than men. There was no significant effect of the decoder's (listener's) gender. A second GLMM estimating SRC found a significant effect of encoder and decoder genders, with women outperforming men. Gamma correlations were significantly greater than zero for women and men decoders. In spite of varying interpretations of gender in each independent rating (ERA and SRC), our results suggest that both men and women decoders were accurate in their metacognition regarding voice emotion recognition. Further research is needed to study how individuals of both genders use metacognitive knowledge in their emotional recognition and whether and how such knowledge contributes to effective social communication.

Hybrid model for speech emotion recognition of normal and autistic children (SERNAC)

Since the last decade, autism spectrum disorder (ASD) has been used as a general term to describe a wide range of conditions, including autistic syndrome, Asperger's disorder, and pervasive developmental disability. This problem emerges as a decreased ability to share emotions and a greater difficulty understanding others' feelings, leading to increased social communication difficulties. To assist patients with ASD, we proposed a concept that incorporates speech emotion detection technologies, which are widely used in the field of human-computer interaction (particularly youngsters). An algorithm based on a novel method for classifying normal and autistic children's speech emotions is implemented in this article. The training data set is treated to a new approach after all features have been extracted. The technique discussed in this study is the creation of a hybrid algorithm that serves as a classifier for normal and autistic children's speech emotions. Voice emotion recognition can be identified accurately and with a lower error rate. The data collection includes speech samples from 200 normal and 250 autistic groups in four moods (Angry, Happy, Neutral and Sad). As per research findings, the implemented hybrid algorithm for Normal and Autistic Children Speech Emotions (SERNAC) outperformed the existing classifiers by increasing accuracy.

You better listen to yourself: studying metacognitive efficiency in emotion recognition by voice

PurposeMetacognition, or the ability to monitor the performance of oneself, is known for its fundamental importance for human behavior adjustments. However, studies of metacognition in social behaviors focused on emotion recognition are relatively scarce. In the current study, we aimed to examine the effectiveness of metacognition, measured by self-rated confidence in voice emotion recognition tasks within healthy individuals.MethodsWe collected 180 audio-recorded lexical sentences portraying discrete emotions: anger, happiness, sadness, fear, surprise, and neutrality expressions. Upon listening to voice stimuli, participants (N = 100; 50 females, 50 males) completed the perception task of recognition of emotion. After each trial, a confidence rating (CR) was assigned.ResultsA series of one-tailed t-tests showed that the differences in mean CRs assigned to correct and incorrect performances were significant for all emotions and neutral expression.ConclusionsOur preliminary results demonstrate efficiency in metacognition of emotion recognition by voice. Theoretically, our results support the difference between accuracy in metacognition, measured by CR, and efficiency in metacognition, as it specified the CR between correct and incorrect performance. To gain better insights into practical issues, further studies are needed to examine whether and what are the differences between accuracy and efficiency in metacognition, as part of social communication.

Human-computer interaction: Evaluation of trust and emotional

With the advancement of information technology, human-computer interaction is becoming increasingly intelligent. This progress has led to the transformation of the car cabin from a simple driving space to an intelligent mobile life terminal. At the same time, more and more people have psychological problems in modern society, and timely adjustment of their negative emotions is of great practical significance to social harmony and stability. Traditional methods of emotion regulation require a lot of manpower and energy. Hence, this paper presents an approach that utilizes text dialogue and somatosensory interaction to detect the users emotions and subsequently adjust them. By examining and analyzing the current research landscape, the objective of this study is to offer insights for designing trustworthy and emotionally-responsive interactions in the automotive context. It can bring a better driving experience to smart car users and bring benefits to many companies. It is of great scientific and application value to carry out this research in depth to promote the development of human-computer interaction. Through literature review, case study, theoretical analysis and other research methods. This paper sorts out the establishment of trust degree and recognition of emotional changes in human-computer interaction, and puts forward the role, defects and improvements of trust establishment in human-car cooperation, as well as the reasons affecting user emotions, and how to improve the defects of the application of voice emotion recognition. It also discusses difficulties in establishing trust and misperception of emotions.

Association between video gaming time and cognitive functions: A cross-sectional study of Chinese children and adolescents.

This study sought to explore relationships between video gaming time and cognitive functioning in children and adolescents to provide a scientific reference for a reasonable time range of game use. A total of 649 participants aged 6-18 years were recruited through an online survey using convenience sampling. We used a combination of multiple linear regression models, smoothing splines, piecewise linear regression models, and log-likelihood ratio tests to comprehensively analyze the linear and nonlinear relationships between video gaming time and cognitive functions. Neurocognitive functioning was assessed using the digit symbol test, spatial span back test, Stroop task, and Wisconsin card sorting test. Facial and voice emotion recognition tests were used to evaluate social cognitive functioning. Video gaming time had a saturation effect on improving correct answers to the digit symbol test, which means that performance did not increase with increasing video gaming time when the video gaming duration reached 20h/week (adjusted β=-0.58; 95% CI: -1.22, 0.05). Furthermore, both the relationship between video gaming time and the Wisconsin Card Sorting Test and the facial emotion recognition score showed a threshold effect. The completed categories of the Wisconsin Card Sorting Test began to decline after 17h/week of playtime, and a decline in facial emotion recognition occurred after playing video games for over 20h/week. These results suggest that children and adolescents should restrict their video gaming time to within a certain range, which could help reduce the negative effects of video games and retain their positive effects.

Speech Emotion Recognition Using Deep Learning

Abstract: Due to different technical developments, speech signals have evolved into a kind of human-machine communication in the digital age. Recognizing the emotions of the person behind his or her speech is a crucial part of Human-Computer Interaction (HCI). Many methods, including numerous well-known speech analysis and classification algorithms, have been employed to extract emotions from signals in the literature on voice emotion recognition (SER). Speech Emotion Recognition (SER) approaches have become obsolete as the Deep Learning concept has come into play. In this paper, the algorithm for identifying speech-based emotions is implemented using deep learning. It also provides an overview of deep learning methodologies and examines some recent research that makes use of these methods. It makes use of a dataset of various emotional voices and then aids in the identification of that emotion. It will be beneficial for the computers or robots to understand humans more clearly and function in accordance with it.

Research on Chinese Speech Emotion Recognition Based on Deep Neural Network and Acoustic Features.

In recent years, the use of Artificial Intelligence for emotion recognition has attracted much attention. The industrial applicability of emotion recognition is quite comprehensive and has good development potential. This research uses voice emotion recognition technology to apply it to Chinese speech emotion recognition. The main purpose of this research is to transform gradually popularized smart home voice assistants or AI system service robots from a touch-sensitive interface to a voice operation. This research proposed a specifically designed Deep Neural Network (DNN) model to develop a Chinese speech emotion recognition system. In this research, 29 acoustic characteristics in acoustic theory are used as the training attributes of the proposed model. This research also proposes a variety of audio adjustment methods to amplify datasets and enhance training accuracy, including waveform adjustment, pitch adjustment, and pre-emphasize. This study achieved an average emotion recognition accuracy of 88.9% in the CASIA Chinese sentiment corpus. The results show that the deep learning model and audio adjustment method proposed in this study can effectively identify the emotions of Chinese short sentences and can be applied to Chinese voice assistants or integrated with other dialogue applications.

Design of Aging Smart Home Products Based on Radial Basis Function Speech Emotion Recognition.

The rapid development of computer technology and artificial intelligence is affecting people’s daily lives, where language is the most common way of communication in people’s daily life. To apply the emotion information contained in voice signals to artificial intelligence products after analysis, this article proposes a design based on voice emotion recognition for aging intelligent home products with RBF. The authors first aimed at a smart home design, and based on the problem of weak adaptability and learning ability of the aging population, a speech emotion recognition method based on a hybrid model of Hidden Markov/Radial Basis Function Neural Network (HMM/RBF) is proposed. This method combines the strong dynamic timing modeling capabilities of the HMM model and the strong classification decision-making ability of the RBF model, and by combining the two models, the speech emotion recognition rate is greatly improved. Furthermore, by introducing the concept of the dynamic optimal learning rate, the convergence speed of the network is reduced to 40.25s and the operation efficiency is optimized. Matlab’s simulation tests show that the recognition speed of the HMM/RBF hybrid model is 9.82–12.28% higher than that of the HMM model and the RBF model alone, confirming the accuracy and superiority of the algorithm and model.

Voice emotion recognition by Mandarin-speaking pediatric cochlear implant users in Taiwan.

ObjectivesTo explore the effects of obligatory lexical tone learning on speech emotion recognition and the cross‐culture differences between United States and Taiwan for speech emotion understanding in children with cochlear implant.MethodsThis cohort study enrolled 60 cochlear‐implanted (cCI) Mandarin‐speaking, school‐aged children who underwent cochlear implantation before 5 years of age and 53 normal‐hearing children (cNH) in Taiwan. The emotion recognition and the sensitivity of fundamental frequency (F0) changes for those school‐aged cNH and cCI (6–17 years old) were examined in a tertiary referred center.ResultsThe mean emotion recognition score of the cNH group was significantly better than the cCI. Female speakers' vocal emotions are more easily to be recognized than male speakers' emotion. There was a significant effect of age at test on voice recognition performance. The average score of cCI with full‐spectrum speech was close to the average score of cNH with eight‐channel narrowband vocoder speech. The average performance of voice emotion recognition across speakers for cCI could be predicted by their sensitivity to changes in F0.ConclusionsBetter pitch discrimination ability comes with better voice emotion recognition for Mandarin‐speaking cCI. Besides the F0 cues, cCI are likely to adapt their voice emotion recognition by relying more on secondary cues such as intensity and duration. Although cross‐culture differences exist for the acoustic features of voice emotion, Mandarin‐speaking cCI and their English‐speaking cCI peer expressed a positive effect for age at test on emotion recognition, suggesting the learning effect and brain plasticity. Therefore, further device/processor development to improve presentation of pitch information and more rehabilitative efforts are needed to improve the transmission and perception of voice emotion in Mandarin.Level of evidence3.

Regional language Speech Emotion Detection using Deep Neural Network

Speaking is the most basic and efficient mode of human contact. Emotions assist people in communicating and understanding others’ viewpoints by transmitting sentiments and providing feedback.The basic objective of speech emotion recognition is to enable computers to comprehend human emotional states such as happiness, fury, and disdain through voice cues. Extensive Effective Method Coefficients of Mel cepstral frequency have been proposed for this problem. The characteristics of Mel frequency ceptral coefficients(MFCC) and the audio based textual characteristics are extracted from the audio characteristics and the hybrid textural framework characteristics of the video are extracted. Voice emotion recognition is used in a variety of applications such as voice monitoring, online learning, clinical investigations, deception detection, entertainment, computer games, and call centres.

Age-Related Changes in Voice Emotion Recognition by Postlingually Deafened Listeners With Cochlear Implants.

Identification of emotional prosody in speech declines with age in normally hearing (NH) adults. Cochlear implant (CI) users have deficits in the perception of prosody, but the effects of age on vocal emotion recognition by adult postlingually deaf CI users are not known. The objective of the present study was to examine age-related changes in CI users' and NH listeners' emotion recognition. Participants included 18 CI users (29.6 to 74.5 years) and 43 NH adults (25.8 to 74.8 years). Participants listened to emotion-neutral sentences spoken by a male and female talker in five emotions (happy, sad, scared, angry, neutral). NH adults heard them in four conditions: unprocessed (full spectrum) speech, 16-channel, 8-channel, and 4-channel noise-band vocoded speech. The adult CI users only listened to unprocessed (full spectrum) speech. Sensitivity (d') to emotions and Reaction Times were obtained using a single-interval, five-alternative, forced-choice paradigm. For NH participants, results indicated age-related declines in Accuracy and d', and age-related increases in Reaction Time in all conditions. Results indicated an overall deficit, as well as age-related declines in overall d' for CI users, but Reaction Times were elevated compared with NH listeners and did not show age-related changes. Analysis of Accuracy scores (hit rates) were generally consistent with d' data. Both CI users and NH listeners showed age-related deficits in emotion identification. The CI users' overall deficit in emotion perception, and their slower response times, suggest impaired social communication which may in turn impact overall well-being, particularly so for older CI users, as lower vocal emotion recognition scores have been associated with poorer subjective quality of life in CI patients.

Voice Emotion Recognition by Mandarin-Speaking Children with Cochlear Implants.

Emotional expressions are very important in social interactions. Children with cochlear implants can have voice emotion recognition deficits due to device limitations. Mandarin-speaking children with cochlear implants may face greater challenges than those speaking nontonal languages; the pitch information is not well preserved in cochlear implants, and such children could benefit from child-directed speech, which carries more exaggerated distinctive acoustic cues for different emotions. This study investigated voice emotion recognition, using both adult-directed and child-directed materials, in Mandarin-speaking children with cochlear implants compared with normal hearing peers. The authors hypothesized that both the children with cochlear implants and those with normal hearing would perform better with child-directed materials than with adult-directed materials. Thirty children (7.17-17 years of age) with cochlear implants and 27 children with normal hearing (6.92-17.08 years of age) were recruited in this study. Participants completed a nonverbal reasoning test, speech recognition tests, and a voice emotion recognition task. Children with cochlear implants over the age of 10 years also completed the Chinese version of the Nijmegen Cochlear Implant Questionnaire to evaluate the health-related quality of life. The voice emotion recognition task was a five-alternative, forced-choice paradigm, which contains sentences spoken with five emotions (happy, angry, sad, scared, and neutral) in a child-directed or adult-directed manner. Acoustic analyses showed substantial variations across emotions in all materials, mainly on measures of mean fundamental frequency and fundamental frequency range. Mandarin-speaking children with cochlear implants displayed a significantly poorer performance than normal hearing peers in voice emotion perception tasks, regardless of whether the performance is measured in accuracy scores, Hu value, or reaction time. Children with cochlear implants and children with normal hearing were mainly affected by the mean fundamental frequency in speech emotion recognition tasks. Chronological age had a significant effect on speech emotion recognition in children with normal hearing; however, there was no significant correlation between chronological age and accuracy scores in speech emotion recognition in children with implants. Significant effects of specific emotion and test materials (better performance with child-directed materials) in both groups of children were observed. Among the children with cochlear implants, age at implantation, percentage scores of nonverbal intelligence quotient test, and sentence recognition threshold in quiet could predict recognition performance in both accuracy scores and Hu values. Time wearing cochlear implant could predict reaction time in emotion perception tasks among children with cochlear implants. No correlation was observed between the accuracy score in voice emotion perception and the self-reported scores of health-related quality of life; however, the latter were significantly correlated with speech recognition skills among Mandarin-speaking children with cochlear implants. Mandarin-speaking children with cochlear implants could have significant deficits in voice emotion recognition tasks compared with their normally hearing peers and can benefit from the exaggerated prosody of child-directed speech. The effects of age at cochlear implantation, speech and language development, and cognition could play an important role in voice emotion perception by Mandarin-speaking children with cochlear implants.

Adaptive algorithm for feature selection of speech emotion recognition based on genetic algorithm and SVM

As a key carrier for people to obtain information in daily life, speech not only provides text signals, but also contains emotional signals. As an important factor of semantics, emotion signals are the focus of improving the intelligent level of human-computer interaction. Therefore, it is important to improving the accuracy of speech emotion recognition. This paper proposes to incorporate derivative feature parameters into the voice emotion recognition feature selection, and to improve the feature selection algorithm based on genetic algorithm and SVM. This article may provide technical support to promote the development of artificial intelligence.

Perception of Child-Directed Versus Adult-Directed Emotional Speech in Pediatric Cochlear Implant Users.

Cochlear implants (CIs) are remarkable in allowing individuals with severe to profound hearing loss to perceive speech. Despite these gains in speech understanding, however, CI users often struggle to perceive elements such as vocal emotion and prosody, as CIs are unable to transmit the spectro-temporal detail needed to decode affective cues. This issue becomes particularly important for children with CIs, but little is known about their emotional development. In a previous study, pediatric CI users showed deficits in voice emotion recognition with child-directed stimuli featuring exaggerated prosody. However, the large intersubject variability and differential developmental trajectory known in this population incited us to question the extent to which exaggerated prosody would facilitate performance in this task. Thus, the authors revisited the question with both adult-directed and child-directed stimuli. Vocal emotion recognition was measured using both child-directed (CDS) and adult-directed (ADS) speech conditions. Pediatric CI users, aged 7-19 years old, with no cognitive or visual impairments and who communicated through oral communication with English as the primary language participated in the experiment (n = 27). Stimuli comprised 12 sentences selected from the HINT database. The sentences were spoken by male and female talkers in a CDS or ADS manner, in each of the five target emotions (happy, sad, neutral, scared, and angry). The chosen sentences were semantically emotion-neutral. Percent correct emotion recognition scores were analyzed for each participant in each condition (CDS vs. ADS). Children also completed cognitive tests of nonverbal IQ and receptive vocabulary, while parents completed questionnaires of CI and hearing history. It was predicted that the reduced prosodic variations found in the ADS condition would result in lower vocal emotion recognition scores compared with the CDS condition. Moreover, it was hypothesized that cognitive factors, perceptual sensitivity to complex pitch changes, and elements of each child's hearing history may serve as predictors of performance on vocal emotion recognition. Consistent with our hypothesis, pediatric CI users scored higher on CDS compared with ADS speech stimuli, suggesting that speaking with an exaggerated prosody-akin to "motherese"-may be a viable way to convey emotional content. Significant talker effects were also observed in that higher scores were found for the female talker for both conditions. Multiple regression analysis showed that nonverbal IQ was a significant predictor of CDS emotion recognition scores while Years using CI was a significant predictor of ADS scores. Confusion matrix analyses revealed a dependence of results on specific emotions; for the CDS condition's female talker, participants had high sensitivity (d' scores) to happy and low sensitivity to the neutral sentences while for the ADS condition, low sensitivity was found for the scared sentences. In general, participants had higher vocal emotion recognition to the CDS condition which also had more variability in pitch and intensity and thus more exaggerated prosody, in comparison to the ADS condition. Results suggest that pediatric CI users struggle with vocal emotion perception in general, particularly to adult-directed speech. The authors believe these results have broad implications for understanding how CI users perceive emotions both from an auditory communication standpoint and a socio-developmental perspective.

Automatic voice emotion recognition of child-parent conversations in natural settings

ABSTRACT While voice communication of emotion has been researched for decades, the accuracy of automatic voice emotion recognition (AVER) is yet to improve. In particular, the intergenerational communication has been under-researched, as indicated by the lack of an emotion corpus on child–parent conversations. In this paper, we presented our work of applying Support-Vector Machines (SVMs), established machine learning models, to analyze 20 pairs of child–parent dialogues on everyday life scenarios. Among many issues facing the emerging work of AVER, we explored two critical ones: the methodological issue of optimising its performance against computational costs, and the conceptual issue on the state of emotionally neutral. We used the minimalistic/extended acoustic feature set extracted with OpenSMILE and a small/large set of annotated utterances for building models, and analyzed the prevalence of the class neutral. Results indicated that the bigger the combined sets, the better the training outcomes. Regardless, the classification models yielded modest average recall when applied to the child–parent data, indicating their low generalizability. Implications for improving AVER and its potential uses are drawn.

Effects of Age and Hearing Loss on the Recognition of Emotions in Speech.

Emotional communication is a cornerstone of social cognition and informs human interaction. Previous studies have shown deficits in facial and vocal emotion recognition in older adults, particularly for negative emotions. However, few studies have examined combined effects of aging and hearing loss on vocal emotion recognition by adults. The objective of this study was to compare vocal emotion recognition in adults with hearing loss relative to age-matched peers with normal hearing. We hypothesized that age would play a role in emotion recognition and that listeners with hearing loss would show deficits across the age range. Thirty-two adults (22 to 74 years of age) with mild to severe, symmetrical sensorineural hearing loss, amplified with bilateral hearing aids and 30 adults (21 to 75 years of age) with normal hearing, participated in the study. Stimuli consisted of sentences spoken by 2 talkers, 1 male, 1 female, in 5 emotions (angry, happy, neutral, sad, and scared) in an adult-directed manner. The task involved a single-interval, five-alternative forced-choice paradigm, in which the participants listened to individual sentences and indicated which of the five emotions was targeted in each sentence. Reaction time was recorded as an indirect measure of cognitive load. Results showed significant effects of age. Older listeners had reduced accuracy, increased reaction times, and reduced d' values. Normal hearing listeners showed an Age by Talker interaction where older listeners had more difficulty identifying male vocal emotion. Listeners with hearing loss showed reduced accuracy, increased reaction times, and lower d' values compared with age-matched normal-hearing listeners. Within the group with hearing loss, age and talker effects were significant, and low-frequency pure-tone averages showed a marginally significant effect. Contrary to other studies, once hearing thresholds were taken into account, no effects of listener sex were observed, nor were there effects of individual emotions on accuracy. However, reaction times and d' values showed significant differences between individual emotions. The results of this study confirm existing findings in the literature showing that older adults show significant deficits in voice emotion recognition compared with their normally hearing peers, and that among listeners with normal hearing, age-related changes in hearing do not predict this age-related deficit. The present results also add to the literature by showing that hearing impairment contributes additionally to deficits in vocal emotion recognition, separate from deficits related to age. These effects of age and hearing loss appear to be quite robust, being evident in reduced accuracy scores and d' measures, as well as in reaction time measures.