论文检索

Yinghao Aaron Li, Xilin Jiang, Fei Tao, Cheng Niu, Kaifeng Xu, Juntong Song, Nima Mesgarani

Diffusion-based text-to-speech (TTS) systems have made remarkable progress in zero-shot speech synthesis, yet optimizing all components for perceptual metrics remains challenging. Prior work with DMOSpeech demonstrated direct metric optimization for speech generation components, but duration prediction remained unoptimized. This paper presents DMOSpeech 2, which extends metric optimization to the duration predictor through a reinforcement learning approach. The proposed system implements a novel duration policy framework using group relative preference optimization (GRPO) with speaker similarity and word error rate as reward signals. By optimizing this previously unoptimized component, DMOSpeech 2 creates a more complete metric-optimized synthesis pipeline. Additionally, this paper introduces teacher-guided sampling, a hybrid approach leveraging a teacher model for initial denoising steps before transitioning to the student model, significantly improving output diversity while maintaining efficiency. Comprehensive evaluations demonstrate superior performance across all metrics compared to previous systems, while reducing sampling steps by half without quality degradation. These advances represent a significant step toward speech synthesis systems with metric optimization across multiple components.

Yi Li, Rui Zhao, Ruiquan Zhang, Jinsong Su, Daimeng Wei, Min Zhang, Yidong Chen

Speech translation (ST) aims to translate speech from a source language into text in the target language. Naturally, speech signals contain paralinguistic cues beyond linguistic content, which could influence or even alter the interpretation of a lexically identical sentence, thereby yielding distinct translations. However, existing ST models lack direct and sufficient modeling of paralinguistic information, which limits their ability to perceive paralinguistic cues and understand speech comprehensively, leading to degraded translation performance. In response, we propose Paralinguistic-aware Speech Translation (PLaST), a novel dual-branch framework which directly leverages paralinguistic cues beyond the linguistic content. Specifically, PLaST employs a speech encoder and a style extractor to independently generate linguistic and paralinguistic representations, respectively. To obtain a purified linguistic representation aligned with the text representation, a hierarchical Optimal Transport (OT) is applied on the layer-wise outputs from an LLM decoder. Then, the paralinguistic information is retrieved and refined with an Attention-based Retrieval (AR) module, with the linguistic representation serving as queries to enable joint guidance for semantic understanding and translation generation. PLaST outperforms the strong baseline with an average of 5.0 directional and 4.5 global contrastive likelihood scores on the paralinguistic-sensitive benchmark ContraProST, demonstrating its superior capability in paralinguistic perception. Further experiments on the standard speech translation benchmark CoVoST-2 show that PLaST generalizes well to typical ST scenarios.

Longhao Li, Zhao Guo, Hongjie Chen, Yuhang Dai, Ziyu Zhang, Hongfei Xue, Tianlun Zuo, Chengyou Wang, Shuiyuan Wang, Xin Xu 等

The development of speech understanding and generation has been significantly accelerated by the availability of large-scale, high-quality speech datasets. Among these, ASR and TTS are regarded as the most established and fundamental tasks. However, for Cantonese (Yue Chinese), spoken by approximately 84.9 million native speakers worldwide, limited annotated resources have hindered progress and resulted in suboptimal ASR and TTS performance. To address this challenge, we propose WenetSpeech-Pipe, an integrated pipeline for building large-scale speech corpus with multi-dimensional annotation tailored for speech understanding and generation. Based on this pipeline, we release WenetSpeech-Yue, the first large-scale Cantonese speech corpus with multi-dimensional annotation for ASR and TTS, covering 21,800 hours across 10 domains with annotations including ASR transcription, text confidence, speaker identity, age, gender, speech quality scores, among other annotations. We also release WSYue-eval, a comprehensive Cantonese benchmark with two components: WSYue-ASR-eval, a manually annotated set for evaluating ASR on short and long utterances, code-switching, and diverse acoustic conditions, and WSYue-TTS-eval, with base and coverage subsets for standard and generalization testing. Experimental results show that models trained on WenetSpeech-Yue achieve competitive results against state-of-the-art (SOTA) Cantonese ASR and TTS systems, including commercial and LLM-based models, highlighting the value of our dataset and pipeline.

Chen Li, Peiji Yang, Yicheng Zhong, Jianxing Yu, Zhisheng Wang, Zihao Gou, Wenqing Chen, Jian Yin

Recent advances in Speech Large Language Models (Speech LLMs) have led to great progress in speech understanding tasks such as Automatic Speech Recognition (ASR) and Speech Emotion Recognition (SER). However, whether these models can achieve human-level auditory perception, particularly in terms of their ability to comprehend latent intentions and implicit emotions in real-world spoken language, remains underexplored. To this end, we introduce the Human-level Perception in Spoken Speech Understanding (HPSU), a new benchmark for fully evaluating the human-level perceptual and understanding capabilities of Speech LLMs. HPSU comprises over 20,000 expert-validated spoken language understanding samples in English and Chinese. It establishes a comprehensive evaluation framework by encompassing a spectrum of tasks, ranging from basic speaker attribute recognition to complex inference of latent intentions and implicit emotions. To address the issues of data scarcity and high cost of manual annotation in real-world scenarios, we developed a semi-automatic annotation process. This process fuses audio, textual, and visual information to enable precise speech understanding and labeling, thus enhancing both annotation efficiency and quality. We systematically evaluate various open-source and proprietary Speech LLMs. The results demonstrate that even top-performing models still fall considerably short of human capabilities in understanding genuine spoken interactions. Consequently, HPSU will be useful for guiding the development of Speech LLMs toward human-level perception and cognition.

Min Ho Jang, Eun Seo Seo, Jin Young Kim, Hyeongsoo Lim, Ji Won Yoon

Recursive transformer (RT) is a promising parameter-sharing technique for reducing computational burden of large-scale model. While RT has been successfully applied to large language models (LLMs), its effectiveness in automatic speech recognition (ASR) remains limited, despite the parallel trend of model scaling in the speech domain. In this paper, we reveal that conventional RT designs for LLMs are suboptimal for speech recognition, primarily because they do not fully consider the layer-wise specialization inherent in the ASR architecture, where lower layers focus on phonetic features and upper layers capture linguistic localization. To address this, we propose BiCycle, a novel RT scheme tailored for ASR. In particular, we firstly analyze attention patterns in a pre-trained ASR model to divide its layers into phonetic and linguistic groups. BiCycle then constructs an efficient RT model by transferring the pre-trained model’s weights in a step-wise manner and applies recursion separately to the phonetic and linguistic groups, preventing conflicts between their roles. Extensive experimental results confirm that the proposed method not only preserves the original ASR mechanism but also outperforms conventional RT approaches.

Jiliang Hu, Zuchao Li, Baoyuan Qi, Guoming Liu, Ping Wang

Significant progress has been made in spoken question answering (SQA) in recent years. However, many existing methods, including large audio language models, struggle with processing long audio. Follow the success of retrieval augmented generation, a speech-related retriever shows promising in help preprocessing long-form speech. But the performance of existing speech-related retrievers is lacking. To address this challenge, we propose CLSR, an end-to-end contrastive language-speech retriever that efficiently extracts question-relevant segments from long audio recordings for downstream SQA task. Unlike conventional speech-text contrastive models, CLSR incorporates an intermediate step that converts acoustic features into text-like representations prior to alignment, thereby more effectively bridging the gap between modalities. Experimental results across four cross-modal retrieval datasets demonstrate that CLSR surpasses both end-to-end speech related retrievers and pipeline approaches combining speech recognition with text retrieval, providing a robust foundation for advancing practical long-form SQA applications.

Nameer Hirschkind, Joseph Liu, Xiao Yu, Mahesh Kumar Nandwana

Simultaneous Speech Translation (SimulST) systems stream in audio while simultaneously emitting translated text or speech. Such systems face the significant challenge of balancing translation quality and latency. We introduce a strategy to optimize this tradeoff: wait for more input only if you gain information by doing so. Based on this strategy, we present Regularized Entropy INformation Adaptation (REINA), a novel loss to train an adaptive policy using an existing non-streaming translation model. We derive REINA from information theory principles and show that REINA helps push the reported Pareto frontier of the latency/quality tradeoff over prior works. Utilizing REINA, we train a SimulST model on French, Spanish and German, both from and into English. Training on only open source or synthetically generated data, we achieve state-of-the-art (SOTA) streaming results for models of comparable size. We also introduce a metric for streaming efficiency, quantitatively showing REINA improves the latency/quality trade-off by as much as 21 percent compared to prior approaches, normalized against non-streaming baseline BLEU scores.

Hong Han, Hao-Chen Pei, Zhao-Zheng Nie, Xin Luo, Xin-Shun Xu

Automatic pronunciation assessment plays a crucial role in computer-assisted pronunciation training systems. Due to the ability to perform multiple pronunciation tasks simultaneously, multi-aspect multi-granularity pronunciation assessment methods are gradually receiving more attention and achieving better performance than single-level modeling tasks. However, existing methods only consider unidirectional dependencies between adjacent granularity levels, lacking bidirectional interaction among phoneme, word, and utterance levels and thus insufficiently capturing the acoustic structural correlations. To address this issue, we propose a novel residual hierarchical interactive method, HIA for short, that enables bidirectional modeling across granularities. As the core of HIA, the Interactive Attention Module leverages an attention mechanism to achieve dynamic bidirectional interaction, effectively capturing linguistic features at each granularity while integrating correlations between different granularity levels. We also propose a residual hierarchical structure to alleviate the feature forgetting problem when modeling acoustic hierarchies. In addition, we use 1-D convolutional layers to enhance the extraction of local contextual cues at each granularity. Extensive experiments on the speechocean762 dataset show that our model is comprehensively ahead of the existing state-of-the-art methods.

Yuan Ge, Junxiang Zhang, Xiaoqian Liu, Bei Li, Xiangnan Ma, Chenglong Wang, Kaiyang Ye, Yangfan Du, Linfeng Zhang, Yuxin Huang 等

Speech-to-Speech (S2S) Large Language Models (LLMs) are foundational to natural human-computer interaction, enabling end-to-end spoken dialogue systems. However, evaluating these models remains a fundamental challenge. We propose SageLM, an end-to-end, multi-aspect, and explainable speech LLM for comprehensive S2S LLMs evaluation. First, unlike cascaded approaches that disregard acoustic features, SageLM jointly assesses both semantic and acoustic dimensions. Second, it leverages rationale-based supervision to enhance explainability and guide model learning, achieving superior alignment with evaluation outcomes compared to rule-based reinforcement learning methods. Third, we introduce SpeechFeedback, a synthetic preference dataset, and employ a two-stage training paradigm to mitigate the scarcity of speech preference data. Trained on both semantic and acoustic dimensions, SageLM achieves an 82.79% agreement rate with human evaluators, outperforming cascaded and SLM-based baselines by at least 7.42% and 26.20%, respectively.

Biao Fu, Donglei Yu, Minpeng Liao, Chengxi Li, Xinjie Chen, Yidong Chen, Kai Fan, Xiaodong Shi

Simultaneous speech translation (SimulST) produces translations incrementally while processing partial speech input. Although large language models (LLMs) have shown strong capabilities in offline translation tasks, applying them to SimulST poses notable challenges. Existing LLM-based SimulST approaches either incur significant computational overhead due to repeated encoding of bidirectional speech encoder, or they depend on a fixed read/write policy, limiting the efficiency and performance. In this work, we introduce Efficient and Adaptive Simultaneous Speech Translation (EASiST) with fully unidirectional architecture, including both speech encoder and LLM. EASiST includes a multi-latency data curation strategy to generate semantically aligned SimulST training samples and redefines SimulST as an interleaved generation task with explicit read/write tokens. To facilitate adaptive inference, we incorporate a lightweight policy head that dynamically predicts read/write actions. Additionally, we employ a multi-stage training strategy to align speech-text modalities and optimize both translation and policy behavior. Experiments on both in-domain (MuST-C) and out-of-domain (Europarl-ST) En-De and En-Es datasets demonstrate that EASiST offers superior latency-quality trade-offs compared to several strong baselines.

Linghan Fang, Tianxin Xie, Li Liu

Recently, Automatic Speech Recognition (ASR) systems (e.g., Whisper) have achieved remarkable accuracy improvements but remain highly sensitive to real-world unseen data (data with large distribution shifts), including noisy environments and diverse accents. To address this issue, test-time adaptation (TTA) has shown great potential in improving the model adaptability at inference time without ground-truth labels, and existing TTA methods often rely on pseudo-labeling or entropy minimization. However, by treating model confidence as a learning signal, these methods may reinforce high-confidence errors, leading to confirmation bias that undermines adaptation. To overcome these limitations, we present ASR-TRA, a novel Test-time Reinforcement Adaptation framework inspired by causal intervention. More precisely, our method introduces a learnable decoder prompt and utilizes temperature-controlled stochastic decoding to generate diverse transcription candidates. These are scored by a reward model that measures audio-text semantic alignment, and the resulting feedback is used to update both model and prompt parameters via reinforcement learning. Comprehensive experiments on LibriSpeech with synthetic noise and L2 Arctic accented English datasets demonstrate that our method significantly outperforms existing state-of-the-art (SOTA), including SUTA and SGEM, in both accuracy and inference speed. Ablation studies further confirm the effectiveness of combining audio and language-based rewards, highlighting our method's enhanced stability and interpretability. Overall, our approach provides a practical and robust solution for deploying ASR systems in challenging real-world conditions.

Xiaoran Fan, Zhichao Sun, Yangfan Gao, Jingfei Xiong, Hang Yan, Yifei Cao, Jiajun Sun, Shuo Li, Zhihao Zhang, Zhiheng Xi 等

Speech-language models (SLMs) offer a promising path toward unifying speech and text understanding and generation. However, challenges remain in achieving effective cross-modal alignment and high-quality speech generation. In this work, we systematically investigate the role of speech tokenizer designs in LLM-centric SLMs, augmented by speech heads and speaker modeling. We compare coupled, semi-decoupled, and fully decoupled speech tokenizers under a fair SLM framework and find that decoupled tokenization significantly improves alignment and synthesis quality. To address the information density mismatch between speech and text, we introduce multi-token prediction (MTP) into SLMs, enabling each hidden state to decode multiple speech tokens. This leads to up to 12× faster decoding and a substantial drop in word error rate (from 6.07 to 3.01). Furthermore, we propose a speaker-aware generation paradigm and introduce RoleTriviaQA, a large-scale role-playing knowledge QA benchmark with diverse speaker identities. Experiments demonstrate that our methods enhance both knowledge understanding and speaker consistency.

Yexing Du, Kaiyuan Liu, Youcheng Pan, Zheng Chu, Bo Yang, Xiaocheng Feng, Ming Liu, Yang Xiang

As Large Language Models (LLMs) are increasingly popularized in the multilingual world, ensuring hallucination-free factuality becomes markedly crucial. However, existing benchmarks for evaluating the reliability of Multimodal Large Language Models (MLLMs) predominantly focus on textual or visual modalities with a primary emphasis on English, which creates a gap in evaluation when processing multilingual input, especially in speech. To bridge this gap, we propose a novel Cross-lingual and Cross-modal Factuality benchmark (CCFQA). Specifically, the CCFQA benchmark contains parallel speech-text factual questions across 8 languages, designed to systematically evaluate MLLMs' cross-lingual and cross-modal factuality capabilities. Our experimental results demonstrate that current MLLMs still face substantial challenges on the CCFQA benchmark. Furthermore, we propose a few-shot transfer learning strategy that effectively transfers the Question Answering (QA) capabilities of LLMs in English to multilingual Spoken Question Answering (SQA) tasks, achieving competitive performance with GPT-4o-mini-Audio using just 5-shot training. We release CCFQA as a foundational research resource to promote the development of MLLMs with more robust and reliable speech understanding capabilities.

Zhongren Dong, Bin Wang, Jing Han, Haotian Guo, Xiaojun Mo, Yimin Cao, Zixing Zhang

Neural Speech Codecs face a fundamental trade-off at low bitrates: preserving acoustic fidelity often compromises semantic richness. To address this, we introduce SACodec, a novel codec built upon an asymmetric dual-quantizer that employs our proposed Semantic Anchoring mechanism. This design strategically decouples the quantization of Semantic and Acoustic details. The semantic anchoring is achieved via a lightweight projector that aligns acoustic features with a frozen, large-scale mHuBERT codebook, injecting linguistic priors while guaranteeing full codebook utilization. Sequentially, for acoustic details, a residual activation module with SimVQ enables a single-layer quantizer (acoustic path) to faithfully recover fine-grained information. At just 1.5 kbps, SACodec establishes a new state of the art by excelling in both fidelity and semantics: subjective listening tests confirm that its reconstruction quality is perceptually highly comparable to ground-truth audio, while its tokens demonstrate substantially improved semantic richness in downstream tasks. This work suggests that assigning specialized semantic quantizers to distinct information streams offers an effective path to reconcile the long-standing trade-off between fidelity, semantics, and modeling simplicity in low-bitrate speech tokenization.

Xiaodong Wang, Langling Huang, Zhirong Wu, Xu Zhao, Teng Xu, Xuhong Xia, Peixi Peng

The development of multimodal large language models (MLLMs) has advanced general video understanding. However, existing video evaluation benchmarks primarily focus on non-interactive videos, such as movies and recordings. To fill this gap, this paper proposes the first omnimodal benchmark for interactive livestream videos, LiViBench. It features a diverse set of 24 tasks, highlighting the perceptual, reasoning, and livestream-specific challenges. To efficiently construct the dataset, we design a standardized semi-automatic annotation workflow that incorporates the human-in-the-loop at multiple stages. The workflow leverages multiple MLLMs to form a multi-agent system for comprehensive video description and uses a seed-question-driven method to construct high-quality annotations. All interactive videos in the benchmark include audio, speech, and real-time comments modalities. To enhance models' understanding of interactive videos, we design tailored two-stage instruction-tuning and propose a Video-to-Comment Retrieval (VCR) module to improve the model's ability to utilize real-time comments. Based on these advancements, we develop LiVi-LLM-7B, an MLLM with enhanced knowledge of interactive livestreams. Experiments show that our model outperforms larger open-source models with up to 72B parameters, narrows the gap with leading proprietary models on LiViBench, and achieves enhanced performance on general video benchmarks, including VideoMME, LongVideoBench, MLVU, and VideoEval-Pro.

Hualei Wang, Yiming Li, Shuo Ma, Hong Liu, Xiangdong Wang

Recent Large Audio-Language Models (LALMs) exhibit impressive capabilities in understanding audio content for conversational QA tasks. However, these models struggle to accurately understand timestamps for temporal localization (e.g., Temporal Audio Grounding) and are restricted to short audio perception, leading to constrained capabilities on fine-grained tasks. We identify three key aspects that limit their temporal localization and long audio understanding: (i) timestamp representation, (ii) architecture, and (iii) data. To address this, we introduce TimeAudio, a novel method that empowers LALMs to connect their understanding of audio content with precise temporal perception. Specifically, we incorporate unique temporal markers to improve time-sensitive reasoning and apply an absolute time-aware encoding that explicitly grounds the acoustic features with absolute time information. Moreover, to realize end-to-end long audio understanding, we introduce a segment-level token merging module to substantially reduce audio token redundancy and enhance the efficiency of information extraction. Due to the lack of suitable datasets and evaluation metrics, we consolidate existing audio datasets into a new dataset focused on temporal tasks and establish a series of metrics to evaluate the fine-grained performance. Evaluations show strong performance across a variety of fine-grained tasks, such as dense captioning, temporal grounding, and timeline speech summarization, which demonstrates TimeAudio's robust temporal localization and reasoning capabilities.

Evgeniia Vu, Andrei Boiarov, Dmitry Vetrov

Generating co-speech gestures in real time requires both temporal coherence and efficient sampling. We introduce a novel framework for streaming gesture generation that extends Rolling Diffusion models with structured progressive noise scheduling, enabling seamless long-sequence motion synthesis while preserving realism and diversity. Our framework is universally compatible with existing diffusion-based gesture generation model, transforming them into streaming methods capable of continuous generation without requiring post-processing. We evaluate our framework on ZEGGS and BEAT, strong benchmarks for real-world applicability. Applied to state-of-the-art baselines on both datasets, it consistently outperforms them, demonstrating its effectiveness as a generalizable and efficient solution for real-time co-speech gesture synthesis. We further propose Rolling Diffusion Ladder Acceleration (RDLA), a new approach that employs a ladder-based noise scheduling strategy to simultaneously denoise multiple frames. This significantly improves sampling efficiency while maintaining motion consistency, achieving up to a 4× speedup with high visual fidelity and temporal coherence in our experiments. Comprehensive user studies further validate our framework’s ability to generate realistic, diverse gestures closely synchronized with the audio input.

Runwu Shi, Chang Li, Jiang Wang, Rui Zhang, Nabeela Khan, Benjamin Yen, Takeshi Ashizawa, Kazuhiro Nakadai

Single-channel audio separation aims to separate individual sources from a single-channel mixture. Most existing methods rely on supervised learning with synthetically generated paired data. However, obtaining high-quality paired data in real-world scenarios is often difficult. This data scarcity can degrade model performance under unseen conditions and limit generalization ability. To this end, in this work, we approach this problem from an unsupervised perspective, framing it as a probabilistic inverse problem. Our method requires only diffusion priors trained on individual sources. Separation is then achieved by iteratively guiding an initial state toward the solution through reconstruction guidance. Importantly, we introduce an advanced inverse problem solver specifically designed for separation, which mitigates gradient conflicts caused by interference between the diffusion prior and reconstruction guidance during inverse denoising. This design ensures high-quality and balanced separation performance across individual sources. Additionally, we find that initializing the denoising process with an augmented mixture instead of pure Gaussian noise provides an informative starting point that significantly improves the final performance. To further enhance audio prior modeling, we design a novel time–frequency attention-based network architecture that demonstrates strong audio modeling capability. Collectively, these improvements lead to significant performance gains, as validated across speech–sound event, sound event, and speech separation tasks.

Abinay Reddy Naini, Fernando Diaz, Carlos Busso

Preference learning has gained significant attention in tasks involving subjective human judgments, such as speech emotion recognition (SER) and image aesthetic assessment. While pairwise frameworks such as RankNet offer robust modeling of relative preferences, they are inherently limited to local comparisons and struggle to capture global ranking consistency. To address these limitations, we propose RankList, a novel listwise preference learning framework that generalizes RankNet to structured list-level supervision. Our formulation explicitly models local and non-local ranking constraints within a probabilistic framework. The paper introduces a log-sum-exp approximation to improve training efficiency. We further extend RankList with skip-wise comparisons, enabling progressive exposure to complex list structures and enhancing global ranking fidelity. Extensive experiments demonstrate the superiority of our method across diverse modalities. On benchmark SER datasets (MSP-Podcast, IEMOCAP, BIIC Podcast), RankList achieves consistent improvements in Kendall's Tau and ranking accuracy compared to standard listwise baselines. We also validate our approach on aesthetic image ranking using the Artistic Image Aesthetics dataset, highlighting its broad applicability. Through ablation and cross-domain studies, we show that RankList not only improves in-domain ranking but also generalizes better across datasets. Our framework offers a unified, extensible approach for modeling ordered preferences in subjective learning scenarios.

Xingqi Lin, Liangyu Chen, Min Wu, Min Zhang, Zhenbing Zeng

Robustness verification is a promising technique for rigorously proving Recurrent Neural Networks (RNNs) robustly. A key challenge is to over-approximate the nonlinear activation functions with linear constraints, which can transform the verification problem into an efficiently solvable linear programming problem. Existing methods over-approximate the nonlinear parts with linear bounding planes individually, which may cause significant over-estimation and lead to lower verification accuracy. In this paper, in order to tightly enclose the three-dimensional nonlinear surface generated by the Hadamard product, we propose a novel truncated rectangular prism formed by two linear relaxation planes and a refinement-driven method to minimize both its volume and surface area for tighter over-approximation. Based on this approximation, we implement a prototype DeepPrism for RNN robustness verification. The experimental results demonstrate that DeepPrism has significant improvement compared with the state-of-the-art approaches in various tasks of image classification, speech recognition and sentiment analysis.