EmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech Emotion Detection

The advancement of text-to-speech and audio generation models necessitates robust benchmarks for evaluating the emotional understanding capabilities of AI systems. Current speech emotion recognition (SER) datasets often exhibit limitations in emotional granularity, privacy concerns, or reliance on acted portrayals. This paper introduces EmoNet-Voice, a new resource for speech emotion detection, which includes EmoNet-Voice Big, a large-scale pre-training dataset (featuring over 4,500 hours of speech across 11 voices, 40 emotions, and 4 languages), and EmoNet-Voice Bench, a novel benchmark dataset with human expert annotations. EmoNet-Voice is designed to evaluate SER models on a fine-grained spectrum of 40 emotion categories with different levels of intensities. Leveraging state-of-the-art voice generation, we curated synthetic audio snippets simulating actors portraying scenes designed to evoke specific emotions. Crucially, we conducted rigorous validation by psychology experts who assigned perceived intensity labels. This synthetic, privacy-preserving approach allows for the inclusion of sensitive emotional states often absent in existing datasets. Lastly, we introduce Empathic Insight Voice models that set a new standard in speech emotion recognition with high agreement with human experts. Our evaluations across the current model landscape exhibit valuable findings, such as high-arousal emotions like anger being much easier to detect than low-arousal states like concentration.

CoMuMDR: Code-mixed Multi-modal Multi-domain corpus for Discourse paRsing in conversations

Discourse parsing is an important task useful for NLU applications such as summarization, machine comprehension, and emotion recognition. The current discourse parsing datasets based on conversations consists of written English dialogues restricted to a single domain. In this resource paper, we introduce CoMuMDR: Code-mixed Multi-modal Multi-domain corpus for Discourse paRsing in conversations. The corpus (code-mixed in Hindi and English) has both audio and transcribed text and is annotated with nine discourse relations. We experiment with various SoTA baseline models; the poor performance of SoTA models highlights the challenges of multi-domain code-mixed corpus, pointing towards the need for developing better models for such realistic settings.

Beyond Classification: Towards Speech Emotion Reasoning with Multitask AudioLLMs

Audio Large Language Models (AudioLLMs) have achieved strong results in semantic tasks like speech recognition and translation, but remain limited in modeling paralinguistic cues such as emotion. Existing approaches often treat emotion understanding as a classification problem, offering little insight into the underlying rationale behind predictions. In this work, we explore emotion reasoning, a strategy that leverages the generative capabilities of AudioLLMs to enhance emotion recognition by producing semantically aligned, evidence-grounded explanations. To support this in multitask AudioLLMs, we introduce a unified framework combining reasoning-augmented data supervision, dual-encoder architecture, and task-alternating training. This approach enables AudioLLMs to effectively learn different tasks while incorporating emotional reasoning. Experiments on IEMOCAP and MELD show that our approach not only improves emotion prediction accuracy but also enhances the coherence and evidential grounding of the generated responses.

ALAS: Measuring Latent Speech-Text Alignment For Spoken Language Understanding In Multimodal LLMs

Large Language Models (LLMs) are widely used in Spoken Language Understanding (SLU). Recent SLU models process audio directly by adapting speech input into LLMs for better multimodal learning. A key consideration for these models is the cross-modal alignment between text and audio modalities, which is a telltale sign as to whether or not LLM is able to associate semantic meaning to audio segments. While various methods exist for fusing these modalities, there is no standard metric to evaluate alignment quality in LLMs. In this work, we propose a new metric, ALAS (Automatic Latent Alignment Score). Our study examines the correlation between audio and text representations across transformer layers, for two different tasks (Spoken Question Answering and Emotion Recognition). We showcase that our metric behaves as expected across different layers and different tasks.

CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training

In our prior works, we introduced a scalable streaming speech synthesis model, CosyVoice 2, which integrates a large language model (LLM) and a chunk-aware flow matching (FM) model, and achieves low-latency bi-streaming speech synthesis and human-parity quality. Despite these advancements, CosyVoice 2 exhibits limitations in language coverage, domain diversity, data volume, text formats, and post-training techniques. In this paper, we present CosyVoice 3, an improved model designed for zero-shot multilingual speech synthesis in the wild, surpassing its predecessor in content consistency, speaker similarity, and prosody naturalness. Key features of CosyVoice 3 include: 1) A novel speech tokenizer to improve prosody naturalness, developed via supervised multi-task training, including automatic speech recognition, speech emotion recognition, language identification, audio event detection, and speaker analysis. 2) A new differentiable reward model for post-training applicable not only to CosyVoice 3 but also to other LLM-based speech synthesis models. 3) Dataset Size Scaling: Training data is expanded from ten thousand hours to one million hours, encompassing 9 languages and 18 Chinese dialects across various domains and text formats. 4) Model Size Scaling: Model parameters are increased from 0.5 billion to 1.5 billion, resulting in enhanced performance on our multilingual benchmark due to the larger model capacity. These advancements contribute significantly to the progress of speech synthesis in the wild. We encourage readers to listen to the demo at https://funaudiollm.github.io/cosyvoice3.

X-ARES: A Comprehensive Framework for Assessing Audio Encoder Performance

We introduces X-ARES (eXtensive Audio Representation and Evaluation Suite), a novel open-source benchmark designed to systematically assess audio encoder performance across diverse domains. By encompassing tasks spanning speech, environmental sounds, and music, X-ARES provides two evaluation approaches for evaluating audio representations: linear fine-tuning and unparameterized evaluation. The framework includes 22 distinct tasks that cover essential aspects of audio processing, from speech recognition and emotion detection to sound event classification and music genre identification. Our extensive evaluation of state-of-the-art audio encoders reveals significant performance variations across different tasks and domains, highlighting the complexity of general audio representation learning.

Audio-to-Audio Emotion Conversion With Pitch And Duration Style Transfer

Given a pair of source and reference speech recordings, audio-to-audio (A2A) style transfer involves the generation of an output speech that mimics the style characteristics of the reference while preserving the content and speaker attributes of the source. In this paper, we propose a novel framework, termed as A2A Zero-shot Emotion Style Transfer (A2A-ZEST), that enables the transfer of reference emotional attributes to the source while retaining its speaker and speech contents. The A2A-ZEST framework consists of an analysis-synthesis pipeline, where the analysis module decomposes speech into semantic tokens, speaker representations, and emotion embeddings. Using these representations, a pitch contour estimator and a duration predictor are learned. Further, a synthesis module is designed to generate speech based on the input representations and the derived factors. This entire paradigm of analysis-synthesis is trained purely in a self-supervised manner with an auto-encoding loss. For A2A emotion style transfer, the emotion embedding extracted from the reference speech along with the rest of the representations from the source speech are used in the synthesis module to generate the style translated speech. In our experiments, we evaluate the converted speech on content/speaker preservation (w.r.t. source) as well as on the effectiveness of the emotion style transfer (w.r.t. reference). The proposal, A2A-ZEST, is shown to improve over other prior works on these evaluations, thereby enabling style transfer without any parallel training data. We also illustrate the application of the proposed work for data augmentation in emotion recognition tasks.

VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection

Audiovisual emotion recognition (AVER) aims to infer human emotions from nonverbal visual-audio (VA) cues, offering modality-complementary and language-agnostic advantages. However, AVER remains challenging due to the inherent ambiguity of emotional expressions, cross-modal expressive disparities, and the scarcity of reliably annotated data. Recent self-supervised AVER approaches have introduced strong multimodal representations, yet they predominantly rely on modality-specific encoders and coarse content-level alignment, limiting fine-grained emotional semantic modeling. To address these issues, we propose VAEmo, an efficient two-stage framework for emotion-centric joint VA representation learning with external knowledge injection. In Stage 1, a unified and lightweight representation network is pre-trained on large-scale speaker-centric VA corpora via masked reconstruction and contrastive objectives, mitigating the modality gap and learning expressive, complementary representations without emotion labels. In Stage 2, multimodal large language models automatically generate detailed affective descriptions according to our well-designed chain-of-thought prompting for only a small subset of VA samples; these rich textual semantics are then injected by aligning their corresponding embeddings with VA representations through dual-path contrastive learning, further bridging the emotion gap. Extensive experiments on multiple downstream AVER benchmarks show that VAEmo achieves state-of-the-art performance with a compact design, highlighting the benefit of unified cross-modal encoding and emotion-aware semantic guidance for efficient, generalizable VA emotion representations.

DEEMO: De-identity Multimodal Emotion Recognition and Reasoning

Emotion understanding is a critical yet challenging task. Most existing approaches rely heavily on identity-sensitive information, such as facial expressions and speech, which raises concerns about personal privacy. To address this, we introduce the De-identity Multimodal Emotion Recognition and Reasoning (DEEMO), a novel task designed to enable emotion understanding using de-identified video and audio inputs. The DEEMO dataset consists of two subsets: DEEMO-NFBL, which includes rich annotations of Non-Facial Body Language (NFBL), and DEEMO-MER, an instruction dataset for Multimodal Emotion Recognition and Reasoning using identity-free cues. This design supports emotion understanding without compromising identity privacy. In addition, we propose DEEMO-LLaMA, a Multimodal Large Language Model (MLLM) that integrates de-identified audio, video, and textual information to enhance both emotion recognition and reasoning. Extensive experiments show that DEEMO-LLaMA achieves state-of-the-art performance on both tasks, outperforming existing MLLMs by a significant margin, achieving 74.49% accuracy and 74.45% F1-score in de-identity emotion recognition, and 6.20 clue overlap and 7.66 label overlap in de-identity emotion reasoning. Our work contributes to ethical AI by advancing privacy-preserving emotion understanding and promoting responsible affective computing.

Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play

A voice AI agent that blends seamlessly into daily life would interact with humans in an autonomous, real-time, and emotionally expressive manner. Rather than merely reacting to commands, it would continuously listen, reason, and respond proactively, fostering fluid, dynamic, and emotionally resonant interactions. We introduce Voila, a family of large voice-language foundation models that make a step towards this vision. Voila moves beyond traditional pipeline systems by adopting a new end-to-end architecture that enables full-duplex, low-latency conversations while preserving rich vocal nuances such as tone, rhythm, and emotion. It achieves a response latency of just 195 milliseconds, surpassing the average human response time. Its hierarchical multi-scale Transformer integrates the reasoning capabilities of large language models (LLMs) with powerful acoustic modeling, enabling natural, persona-aware voice generation -- where users can simply write text instructions to define the speaker's identity, tone, and other characteristics. Moreover, Voila supports over one million pre-built voices and efficient customization of new ones from brief audio samples as short as 10 seconds. Beyond spoken dialogue, Voila is designed as a unified model for a wide range of voice-based applications, including automatic speech recognition (ASR), Text-to-Speech (TTS), and, with minimal adaptation, multilingual speech translation. Voila is fully open-sourced to support open research and accelerate progress toward next-generation human-machine interactions.