Related papers: AffectCodec: Emotion-Preserving Neural Speech Code…

Audio codecs based on discretized neural autoencoders have recently been developed and shown to provide significantly higher compression levels for comparable quality speech output. However, these models are tightly coupled with speech…

Neural audio codecs have revolutionized audio processing by enabling speech tasks to be performed on highly compressed representations. Recent work has shown that speech separation can be achieved within these compressed domains, offering…

Understanding speaker's feelings and producing appropriate responses with emotion connection is a key communicative skill for empathetic dialogue systems. In this paper, we propose a simple technique called Affective Decoding for empathetic…

Emotions widely affect human decision-making. This fact is taken into account by affective computing with the goal of tailoring decision support to the emotional states of individuals. However, the accurate recognition of emotions within…

Speech emotion recognition is a challenging task, and extensive reliance has been placed on models that use audio features in building well-performing classifiers. In this paper, we propose a novel deep dual recurrent encoder model that…

Large language models have revolutionized natural language processing through self-supervised pretraining on massive datasets. Inspired by this success, researchers have explored adapting these methods to speech by discretizing continuous…

Emotion Prediction in Conversation (EPC) aims to forecast the emotions of forthcoming utterances by utilizing preceding dialogues. Previous EPC approaches relied on simple context modeling for emotion extraction, overlooking fine-grained…

Speech Emotion Captioning (SEC) has emerged as a notable research direction. The inherent complexity of emotional content in human speech makes it challenging for traditional discrete classification methods to provide an adequate…

Computational communication research on information has been prevalent in recent years, as people are progressively inquisitive in social behavior and public opinion. Nevertheless, it is of great significance to analyze the direction of…

In this work, we tackle a problem of speech emotion classification. One of the issues in the area of affective computation is that the amount of annotated data is very limited. On the other hand, the number of ways that the same emotion can…

Speech codecs are traditionally optimized for waveform fidelity, allocating bits to preserve acoustic detail even when much of it can be inferred from linguistic structure. This leads to inefficient compression and suboptimal performance on…

Neural audio codecs (NACs), which use neural networks to generate compact audio representations, have garnered interest for their applicability to many downstream tasks -- especially quantized codecs due to their compatibility with large…

Recent advances in speech spoofing necessitate stronger verification mechanisms in neural speech codecs to ensure authenticity. Current methods embed numerical watermarks before compression and extract them from reconstructed speech for…

Affect is an emotional characteristic encompassing valence, arousal, and intensity, and is a crucial attribute for enabling authentic conversations. While existing text-to-speech (TTS) and speech-to-speech systems rely on strength embedding…

Human emotional expression is inherently dynamic, complex, and fluid, characterized by smooth transitions in intensity throughout verbal communication. However, the modeling of such intensity fluctuations has been largely overlooked by…

This paper presents a new neural speech compression method that is practical in the sense that it operates at low bitrate, introduces a low latency, is compatible in computational complexity with current mobile devices, and provides a…

Learning the latent representation of data in unsupervised fashion is a very interesting process that provides relevant features for enhancing the performance of a classifier. For speech emotion recognition tasks, generating effective…

Conversational Speech Synthesis (CSS) aims to accurately express an utterance with the appropriate prosody and emotional inflection within a conversational setting. While recognising the significance of CSS task, the prior studies have not…

Speech Emotion Captioning (SEC) leverages large audio-language models to generate rich, context-aware affective descriptions from speech. However, real-world deployment remains challenging due to the substantial computational demands on…

Word embeddings are one of the most useful tools in any modern natural language processing expert's toolkit. They contain various types of information about each word which makes them the best way to represent the terms in any NLP task. But…