相关论文: Revealing Emotional Clusters in Speaker Embeddings…

Emotional state of a speaker is found to have significant effect in speech production, which can deviate speech from that arising from neutral state. This makes identifying speakers with different emotions a challenging task as generally…

Speaker recognition deals with recognizing speakers by their speech. Most speaker recognition systems are built upon two stages, the first stage extracts low dimensional correlation embeddings from speech, and the second performs the…

Pre-trained deep learning embeddings have consistently shown superior performance over handcrafted acoustic features in speech emotion recognition (SER). However, unlike acoustic features with clear physical meaning, these embeddings lack…

Speech emotion recognition (SER) is a key technology to enable more natural human-machine communication. However, SER has long suffered from a lack of public large-scale labeled datasets. To circumvent this problem, we investigate how…

Deep speaker embeddings have become the leading method for encoding speaker identity in speaker recognition tasks. The embedding space should ideally capture the variations between all possible speakers, encoding the multiple acoustic…

Pre-trained models (PTMs) have shown great promise in the speech and audio domain. Embeddings leveraged from these models serve as inputs for learning algorithms with applications in various downstream tasks. One such crucial task is Speech…

Recent studies have explored the use of pre-trained embeddings for speech emotion recognition (SER), achieving comparable performance to conventional methods that rely on low-level knowledge-inspired acoustic features. These embeddings are…

State-of-the-art speaker verification systems are inherently dependent on some kind of human supervision as they are trained on massive amounts of labeled data. However, manually annotating utterances is slow, expensive and not scalable to…

Speaker identification typically involves three stages. First, a front-end speaker embedding model is trained to embed utterance and speaker profiles. Second, a scoring function is applied between a runtime utterance and each speaker…

We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed-size speaker embedding from a spoken utterance…

Modeling the rich prosodic variations inherent in human speech is essential for generating natural-sounding speech. While speaker embeddings are commonly used as conditioning inputs in personalized speech generation, they are typically…

A great challenge in speaker representation learning using deep models is to design learning objectives that can enhance the discrimination of unseen speakers under unseen domains. This work proposes a supervised contrastive learning…

Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning,…

Depression detection from speech has attracted a lot of attention in recent years. However, the significance of speaker-specific information in depression detection has not yet been explored. In this work, we analyze the significance of…

Emotion recognition models using audio input data can enable the development of interactive systems with applications in mental healthcare, marketing, gaming, and social media analysis. While the field of affective computing using audio…

Speech emotion recognition (SER) models typically rely on costly human-labeled data for training, making scaling methods to large speech datasets and nuanced emotion taxonomies difficult. We present LanSER, a method that enables the use of…

There are individual differences in expressive behaviors driven by cultural norms and personality. This between-person variation can result in reduced emotion recognition performance. Therefore, personalization is an important step in…

Overlapping speech diarization is always treated as a multi-label classification problem. In this paper, we reformulate this task as a single-label prediction problem by encoding the multi-speaker labels with power set. Specifically, we…

Representation learning for speech emotion recognition is challenging due to labeled data sparsity issue and lack of gold standard references. In addition, there is much variability from input speech signals, human subjective perception of…

Inducing semantic representations directly from speech signals is a highly challenging task but has many useful applications in speech mining and spoken language understanding. This study tackles the unsupervised learning of semantic…