AffectCodec is an emotion-guided neural speech codec that preserves emotional cues during quantization while maintaining semantic fidelity and prosodic naturalness.
hub Canonical reference
GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot
Canonical reference. 77% of citing Pith papers cite this work as background.
35
Pith papers citing it
Background
77% of classified citations
abstract
We introduce GLM-4-Voice, an intelligent and human-like end-to-end spoken chatbot. It supports both Chinese and English, engages in real-time voice conversations, and varies vocal nuances such as emotion, intonation, speech rate, and dialect according to user instructions. GLM-4-Voice uses an ultra-low bitrate (175bps), single-codebook speech tokenizer with 12.5Hz frame rate derived from an automatic speech recognition (ASR) model by incorporating a vector-quantized bottleneck into the encoder. To efficiently transfer knowledge from text to speech modalities, we synthesize speech-text interleaved data from existing text pre-training corpora using a text-to-token model. We continue pre-training from the pre-trained text language model GLM-4-9B with a combination of unsupervised speech data, interleaved speech-text data, and supervised speech-text data, scaling up to 1 trillion tokens, achieving state-of-the-art performance in both speech language modeling and spoken question answering. We then fine-tune the pre-trained model with high-quality conversational speech data, achieving superior performance compared to existing baselines in both conversational ability and speech quality. The open models can be accessed through https://github.com/THUDM/GLM-4-Voice and https://huggingface.co/THUDM/glm-4-voice-9b.
hub tools
citation-role summary
background 10
method 2
baseline 1
citation-polarity summary
representative citing papers
Channel fusion gives better semantic grounding and QA performance in full-duplex LLM dialogue but is vulnerable to context corruption during interruptions, while cross-attention routing is more robust at the cost of weaker integration.
VITA-QinYu is the first expressive end-to-end spoken language model supporting role-playing and singing alongside conversation, trained on 15.8K hours of data and outperforming prior models on expressiveness and conversational benchmarks.
SpeechParaling-Bench is a new evaluation framework for paralinguistic-aware speech generation that reveals major limitations in current large audio-language models.
AudioHijack generates imperceptible adversarial audio via gradient estimation, attention supervision, and reverberation blending to hijack 13 LALMs with 79-96% success on unseen contexts and real commercial agents.
RoleJudge is a multidimensional evaluation framework for speech-character alignment in audio LLMs, backed by the RoleChat dataset and multi-stage RL training with standard alignment to reduce reward issues.
HumDial-EIBench is a new benchmark using real human dialogues to evaluate audio language models on emotional intelligence tasks including multi-turn tracking, causal reasoning, empathy generation, and acoustic-semantic conflict resolution.
TiCo enables spoken dialogue models to follow explicit time constraints in generated responses using Spoken Time Markers and reinforcement learning with verifiable rewards, cutting duration error by 2.7x over its backbone.
Spoken language models exhibit style amnesia and fail to maintain instructed paralinguistic styles across multi-turn conversations, with explicit recall offering partial mitigation.
ViBES introduces a speech-language-behavior model using modality-specific transformer experts that jointly generates dialogue and 3D body actions, showing gains over separate co-speech and text-to-motion baselines on multi-turn metrics.
AudioRole provides 1M+ character-grounded audio-text dialogues from TV series plus ARP-Eval to train and measure audio role-playing models, with ARP-Model showing 0.31 acoustic and 0.36 content personalization scores.
LaSR improves context-aware terminology recognition in speech LLMs by aligning latent CoT supervision on acoustic regions and introducing latent reasoning periods, shown on a new academic corpus to outperform standard fine-tuning without added latency.
A wait-think-answer controller for LALMs is trained via SFT followed by six-reward DAPO, raising row-weighted accuracy from 67.6% to 70.3% and cutting post-endpoint thinking length by 14% on synthetic spoken QA while remaining functional on real recorded audio.
Rule-generated preference data aligned via sequential DPO and KTO reduces musical constraint violations and improves coherence in lyric-to-melody generation over baselines.
GRM ranks Mel bands by attack contribution versus utility sensitivity, perturbs a subset, and learns a universal perturbation to reach 88.46% average jailbreak success rate with improved attack-utility trade-off on four audio LLMs.
A multi-stage training method for LLM-based ASR uses new entropy allocation metrics to achieve competitive benchmark performance with 2.3B parameters while mitigating hallucinations via better encoder-LLM decoupling.
FastTurn unifies acoustic features and streaming CTC decoding for low-latency, robust turn detection in full-duplex dialogue systems and releases a realistic human-dialogue test set.
MPS proposes a dual-brain architecture separating formulation reasoning from articulation to achieve real-time CoT in SLMs with accuracy comparable to full pre-computation but much lower latency.
StableToken introduces a multi-branch architecture with bit-wise voting to create noise-robust semantic speech tokens, achieving lower Unit Edit Distance and better SpeechLLM robustness than prior single-path tokenizers.
Step-Audio 2 integrates a latent audio encoder, reasoning-centric reinforcement learning, and discrete audio token generation into language modeling to deliver state-of-the-art performance on audio understanding and conversational benchmarks.
Step-Audio introduces a 130B-parameter unified speech-text model with open-sourced components for understanding, generation, affordable voice cloning, and dynamic control, claiming SOTA human evaluation results on a new benchmark.
PRR accelerates dynamic sparse attention decoding in long-context LLMs via EMA-based prediction, speculative attention, and FlashAttention repair, achieving up to 40% latency reduction.
Sympatheia introduces a continuous affect-conditioned speech dialogue model and the Sympatheia-18k synthetic dataset, showing improved emotional appropriateness over baselines when speech cues are limited.
A survey of Large Audio Language Models that establishes a taxonomy of trustworthiness vulnerabilities and proposes a Defense-in-Depth roadmap for audio intelligence.
citing papers explorer
-
How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken Dialogue
Channel fusion gives better semantic grounding and QA performance in full-duplex LLM dialogue but is vulnerable to context corruption during interruptions, while cross-attention routing is more robust at the cost of weaker integration.
-
Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection
AudioHijack generates imperceptible adversarial audio via gradient estimation, attention supervision, and reverberation blending to hijack 13 LALMs with 79-96% success on unseen contexts and real commercial agents.
-
Character Beyond Speech: Leveraging Role-Playing Evaluation in Audio Large Language Models via Reinforcement Learning
RoleJudge is a multidimensional evaluation framework for speech-character alignment in audio LLMs, backed by the RoleChat dataset and multi-stage RL training with standard alignment to reduce reward issues.
-
GRM: Utility-Aware Jailbreak Attacks on Audio LLMs via Gradient-Ratio Masking
GRM ranks Mel bands by attack contribution versus utility sensitivity, perturbs a subset, and learns a universal perturbation to reach 88.46% average jailbreak success rate with improved attack-utility trade-off on four audio LLMs.
-
Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs
A multi-stage training method for LLM-based ASR uses new entropy allocation metrics to achieve competitive benchmark performance with 2.3B parameters while mitigating hallucinations via better encoder-LLM decoupling.
-
FastTurn: Unifying Acoustic and Streaming Semantic Cues for Low-Latency and Robust Turn Detection
FastTurn unifies acoustic features and streaming CTC decoding for low-latency, robust turn detection in full-duplex dialogue systems and releases a realistic human-dialogue test set.
-
A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook
A survey of Large Audio Language Models that establishes a taxonomy of trustworthiness vulnerabilities and proposes a Defense-in-Depth roadmap for audio intelligence.
-
Fast Text-to-Audio Generation with One-Step Sampling via Energy-Scoring and Auxiliary Contextual Representation Distillation
A one-step text-to-audio model using energy-distance training and contextual distillation outperforms prior fast baselines on AudioCaps and achieves up to 8.5x faster inference than the multi-step IMPACT system with competitive quality.
-
Toward Native Multimodal Modeling: A Roadmap
A roadmap that defines architectural nativity for multimodal models and categorizes them into Multi-to-Text, Multi-to-Target, and Multi-to-Multi types while outlining an industrial pipeline toward unified transformer-based native multimodal modeling.
-
A Survey of Audio Reasoning in Multimodal Foundation Models
A survey that provides a unified formulation of audio reasoning and reviews advances across Audio-to-Text, Audio-to-Speech, Audio-Visual, and Agentic paradigms while discussing challenges and future directions.