arXiv subjects

Lei Xie

Publications and source records attributed to Lei Xie.

At least 37 records · Page 2Linked to original sources

arXiv2026

Preference Optimization with LALM Feedback for Continuous Autoregressive Non-Verbal Vocalization Generation

We propose a preference optimization framework with Large Audio-Language Model (LALM) feedback for controllable non-verbal vocalization (NVV) generation in continuous autoregressive speech models. To construct preference data without human preference annotation, we build a bilingual prompt corpus by combining NVV-injected real transcripts with LLM-generated semantically aligned prompts, perform stochastic model rollouts, and use a LALM to rank candidate utterances and form same-prompt chosen--rejected pairs. We then adopt a two-stage optimization strategy: Rejection Sampling Fine-Tuning (RSFT) first adapts the model to LALM-selected high-scoring samples, followed by Anchored Flow-DPO, which formulates pairwise preference optimization using utterance-level flow-matching loss and retains the chosen-sample flow-matching objective as an SFT anchor. This design enables DPO-style preference learning without explicit sequence likelihoods while preserving direct supervision on preferred realizations. On the official 1,600-utterance NVVSpeech Challenge Track~2 test set, our method achieves a Final Track2Score of \textbf{75.80} (79.39 ZH / 72.21 EN), outperforming the VoxCPM2 baseline by \textbf{+1.84}. The improvements are mainly driven by higher NVV Accuracy and NVV Perceptual Effect, while Overall Quality remains stable.

eess.AS↗

arXiv2026

Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge

Non-verbal vocalizations (NVVs) carry important paralinguistic information but are often omitted by conventional automatic speech recognition (ASR) systems. The ISCSLP NVVSpeech Challenge requires joint transcription of lexical content and 16 NVV categories under limited and highly imbalanced supervision. We present a data-centric NVV-aware ASR pipeline based on cross-dataset label harmonization and a two-stage sampling schedule. We map heterogeneous source labels to the official taxonomy and exclude samples without a reliable mapping. Our schedule first uses square-root category sampling to moderate the long-tailed distribution and then applies uniform-category fine-tuning. On a fixed local validation split, square-root category sampling performs best among the tested single-stage settings. The final two-stage system obtains an official score of 63.86 and ranks fourth in Track 1.

eess.AS↗

arXiv2026

The Second MLC-SLM Challenge: Multilingual Conversational Speech Diarization, Recognition, and Understanding

This paper summarizes the Interspeech2026 second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge, which aims to advance the development of effective multilingual conversational speech language models. We describe the two challenge tasks: multilingual conversational speech diarization and recognition, and multilingual conversational speech understanding, together with the released real-world conversational speech dataset, evaluation protocols, and baseline systems. The challenge attracted 91 teams worldwide, with 704 valid leaderboard results and 14 technical reports across the two tasks. Based on the participating systems, we summarize representative approaches and distill practical insights into multilingual conversational speech recognition and understanding to support future research in the community.

eess.AS↗

arXiv2026

Interactive TTS: Dynamic Speaking Style Adaptation for Expressive Speech Synthesis

Dynamic speaking style adaptation in multi-turn multimodal interaction remains a major challenge for text-to-speech (TTS) systems. Existing context-aware TTS (CTTS) methods typically map dialogue context to speech in an end-to-end manner. Such implicit modeling makes contextual style decisions difficult to supervise, while the entanglement of style, timbre, and content often leads to weak instruction-following and severe timbre drift across turns. To overcome these limitations, we propose Interactive TTS, a dynamic, style-adaptive framework for contextually appropriate and speaker-consistent speech generation. Interactive TTS decouples the process by explicitly modeling contextual style decisions as executable instructions. To bridge the gap between style decisions and speech generation, we introduce Iterative Rejection Sampling Fine-Tuning (Iterative RSFT) and Context-Aware Direct Preference Optimization (CADPO), which significantly enhance instruction-following and align the generated speech with conversational contexts. Extensive experiments demonstrate that Interactive TTS outperforms state-of-the-art models on VStyle and SpeechParaling-Bench. Demo is available at https://wjtian-wonderful.github.io/InteractiveTTS/

eess.AS↗

arXiv2026

StreamTN: A Low-Latency Streaming Chinese Text Normalization Model for Streaming TTS in Dialogue Systems

Text-to-Speech (TTS) is an essential module that provides spoken responses in a spoken dialogue system (SDS) centered on a large language model (LLM). To ensure accurate TTS synthesis, responses generated by an LLM must be converted into TTS-readable formats via a Text Normalization (TN) module, imposing strict low-latency requirements in real-time SDS scenarios. Existing TN solutions are largely rule-based, rely on manual engineering, and generalize poorly to unseen patterns. Although an LLM itself can perform TN through prompt engineering, it faces key limitations: high first-token latency due to non-streaming processing, hallucination risks, and degraded intelligence or reasoning when the core LLM module is fine-tuned solely for TN. To address these challenges, we propose StreamTN, a lightweight LLM-based Chinese streaming TN model. Built on Qwen3-0.6B, StreamTN employs a dual-track streaming framework in which input tokens and output tokens are processed on two parallel tracks, enabling low-latency real-time inference without complex prompting. Moreover, task-specific fine-tuning yields superior TN performance and fewer hallucinations than rule-based systems and general-purpose LLMs. We also introduce a TN benchmark that spans diverse text scenarios, providing a comprehensive evaluation standard for speech generation in spoken dialogue systems. Experiments demonstrate the effectiveness of StreamTN in accuracy and inference latency.

eess.AS↗

arXiv2026

Rethinking Music Tokenization: A Semantic Codec toward High-Fidelity LLM Music Generation

Discrete audio tokenization has become the critical interface between raw waveforms and autoregressive modeling in recent music generation. As a result, music tokenizers must simultaneously support high-fidelity reconstruction and produce discrete sequences that remain amenable to language modeling. Existing reconstruction-oriented tokenizers often mix musical structure with fine acoustic details, producing high-entropy tokens that are hard to model. In contrast, semantics-guided alternatives are designed for speech and do not fit music well, often hurting reconstruction quality. We address these trade-offs by rethinking music tokenization around a measurable notion of music semantic content grounded in downstream Music Information Retrieval tasks. Guided by this definition, we propose MuSeC, a music semantic codec that factorizes semantic and acoustic content directly from mixed signals without source separation. MuSeC preserves information required for high-fidelity reconstruction while producing more LM-friendly discrete units. Empirically, it improves reconstruction quality and yields more predictable token sequences, providing a practical foundation toward high-fidelity LLM music generation. Demos are available at https://longwaytog0.github.io/MuSeC/.

eess.AS↗

arXiv2026

Multimodal Conversational Context for LLM-Based ASR: Data Construction, Training, and Benchmark

Conversational context provides semantic and acoustic cues across turns for automatic speech recognition (ASR), but relying on historical transcripts can propagate recognition errors and discard pronunciation and speaker information. We present a multimodal conversational-context framework for LLM-based ASR that integrates a scenario-controlled data pipeline, scalable multimodal context training, and systematic evaluation. We construct dialogues around entities and their confusable forms and interleave historical user speech with assistant text responses for supervised fine-tuning. We also introduce MM-ContextASR Bench, which evaluates contextual understanding and entity error correction across five scenarios. Experiments with Qwen3-Omni and Step-Audio-2-mini reveal limitations in handling irrelevant and erroneous history and show that our data construction and training improve context utilization, with multimodal context achieving the highest overall entity recall on both models. Further experiments on accent, dialect, and target-speaker ASR demonstrate the value of historical speech. The benchmark data and evaluation code are publicly available at https://github.com/llh666521/MM-ContextASR.

eess.AS↗

arXiv2026

Qwen-Music Technical Report

We introduce Qwen-Music, a music generation model that produces high-fidelity songs with complete vocals. It supports text-to-music generation from descriptions, lyrics, and musical attributes, and cover song generation with different styles and vocal characteristics. Qwen-Music comprises three components: Qwen-Music-Tokenizer, Qwen-Music-LLM, and Qwen-Music-Render. The tokenizer compresses audio into a 25 Hz single-codebook stream of Music Semantic Tokens that preserve semantic and melodic information. The LLM performs autoregressive modeling with a melody-token-based chain-of-thought (Melody-CoT) mechanism that plans melodies before full-song generation, improving musicality, structural coherence, and reference-melody preservation. The renderer enriches discrete semantic tokens with acoustic details to produce high-fidelity stereo waveforms. We train the LLM using a quality-aware pre-training curriculum followed by progressive post-training with supervised initialization, offline DPO, and online GSPO to improve musicality and instruction following. On 600 evaluation inputs, Qwen-Music achieves state-of-the-art results in 13 of 16 objective musicality and audio-quality metrics. Professional evaluators also prefer Qwen-Music over leading proprietary systems. For cover generation, Qwen-Music preserves reference melodies more accurately than Suno V5.5, Suno V5, and MiniMax Cover on the AI-generated reference set, and outperforms MiniMax Cover on most metrics on the real-world popular-song reference set.

cs.SD↗

arXiv2026

Modeling, Scaling, and Decoding: Optimizing Controllable Speech Generation with Nonverbal Vocalizations

Controllable synthesis of nonverbal vocalizations (NVVs) is es- sential for natural and expressive speech, but remains challeng- ing due to their acoustic diversity and imbalanced distribution in existing corpora. To address these challenges, we develop an NVV-aware DiTAR system that models continuous speech latents, encodes the 16 target NVV categories as dedicated to- kens, and adapts stop prediction to distinguish mid-utterance vocalizations from utterance boundaries. Training begins with large-scale bilingual pre-training on diverse NVV speech, fol- lowed by continued supervised fine-tuning on a corpus en- hanced through targeted synthetic augmentation and frequency- aware rebalancing. At inference time, we select the acoustic prompt, tune the LM-guidance and noise-injection scales, and apply Best-of-N sampling with multi-metric selection to re- duce generation failures. The final system achieves an official weighted bilingual score of 62.786, ranking first in Mandarin, second in English, and first overall among participating systems in Track 2 of the ISCSLP 2026 NVVSpeech Challenge. Ab- lation studies show that targeted augmentation benefits under- represented NVV categories the most, while robust candidate selection requires balancing NVV correctness, lexical fidelity, and perceptual quality.

eess.AS↗

arXiv2026

Bridging the Modality Gap in Long-Form Clinical Audio: A Comparative Study of Lightweight and Heavyweight End-to-End SOAP Generation

Automating clinical documentation from long-form doctor-patient conversations remains challenging for modern audio-language models. While cascaded ASR systems perform well, end-to-end (E2E) models often struggle with information loss and hallucinations on extended audio. For the BeTraC 2026 challenge, the ASLP team presents a fully E2E multimodal system that generates structured SOAP notes directly from audio, bypassing intermediate transcripts. We constructed a 1.41-million-sample multi-task corpus and applied a multi-stage pipeline: domain pre-training, supervised fine-tuning, and reward optimization. Evaluating the architecture under both Lightweight (3B) and Heavyweight (30B) constraints reveals that each training stage progressively enhances performance. Furthermore, scaling to 30B parameters substantially boosts concept extraction and summarization quality. Ultimately, our E2E systems consistently outperform representative cascaded ASR+LLM baselines, proving the efficacy of direct multimodal optimization for clinical documentation.

cs.SD↗

arXiv2026

Bridging Data, Reasoning, and Alignment: A Unified Framework for Context-Aware Instruction-Following TTS

The ISCSLP 2026 CoT-TTS Challenge requires TTS systems to generate Chain-of-Thought (CoT) reasoning from dialogue history before synthesizing contextually appropriate speech. While the official baseline establishes a unified architecture, it remains constrained by limited contextual comprehension, weak instruction fidelity, and suboptimal audio quality. We present a systematic optimization pipeline to address these limitations. First, we develop a data process framework that cleans raw data via FullSubNet denoising, Qwen3-ASR re-transcription, and Qwen3.5-35B-A3B-based history-CoT consistency analysis, while distilling 545K high-fidelity instruction samples using Qwen3-TTS and Seed-VC under strict quality filtration. Second, we propose a Context-Aware Direct Preference Optimization (CA-DPO) method. By employing a cascaded filtering strategy, ASR prescreening, LLM tournament ranking, and speaker similarity verification, we obtain high-confidence preference pairs that significantly enhance holistic ``Context$\rightarrow$CoT$\rightarrow$Speech'' consistency during DPO training. Third, we establish an evaluation method featuring a 500-sample test set and an LLM-as-Judge framework to independently assess reasoning and execution fidelity. Experiments demonstrate that our system significantly outperforms the baseline across all objective and subjective metrics, validating our data governance and alignment strategies.

eess.AS↗

arXiv2026

DiTAR+: Dual Optimization for Robust Autoregressive Diffusion Speech Synthesis

Continuous-latent Autoregressive Diffusion Transformer (AR-DiT) models have demonstrated immense potential in zero-shot speech generation. However, they still suffer from limited decoding stability when synthesizing long utterances or complex linguistic structures. This instability primarily stems from a restricted historical receptive field and an acoustic inertia dependency within the diffusion decoder, which causes the model to ignore semantic conditions. To address these challenges, we propose DiTAR+, a dual-optimization framework. First, we introduce Dilated Context Sampling to expand the macro-level historical receptive field without violating physical temporal continuity, thereby preventing cumulative error propagation. Second, we propose Hierarchical Acoustic Masking to prevent shallow layers from attending to acoustic pre-context, explicitly decoupling semantic alignment from acoustic detail reconstruction. Extensive experiments show that our framework effectively mitigates pronunciation errors and semantic hallucinations, enhances generation robustness on challenging sentences, and maintains exceptionally high speaker similarity throughout the entirety of long-form utterances. On the linguistically challenging ZH-Hard set, DiTAR+ reduces the word error rate from 12.478% to 9.893%, and on extended utterances of 25 to 35 seconds it improves speaker similarity from 0.741 to 0.759 while simultaneously lowering the word error rate from 2.778% to 2.173%, outperforming both discrete-token and pure flow-matching baselines.

cs.SD↗

arXiv2026

X-Pred MeanFlow for Streaming Token-to-Mel Speech Decoding

Recent advancements in discrete token-based speech generation have highlighted the importance of efficient token-to-waveform synthesis in streaming and dialogue scenarios. Flow-matching acoustic decoders achieve high-quality token-to-mel generation, but their iterative sampling requires multiple neural function evaluations, limiting low-latency speech synthesis. MeanFlow reduces the sampling budget by modeling the average velocity over a temporal interval, yet maintaining high acoustic quality under extremely few-step token-to-mel generation remains challenging. To address this challenge, we propose X-Pred MeanFlow, a few-step streaming token-to-mel decoder that reparameterizes MeanFlow with mel-space prediction. The decoder predicts a generalized mel field and analytically derives the corresponding average velocity for sampling, thereby preserving the MeanFlow formulation while providing a direct acoustic prediction target. We further introduce layer-selective block-wise attention to enable continuous chunk-wise generation with bounded context. Experiments show that X-Pred MeanFlow improves few-step token-to-mel synthesis over Direct-$u$ MeanFlow and supports stable streaming generation. Speech samples are available.https://renxiaming.github.io/xpred-meanflow-stream-demo

eess.AS↗

arXiv2026

Complex-Text Robustness Evaluation and Failure Diagnosis for Low-Resource Multilingual Text-to-Speech

Low-resource multilingual text-to-speech (TTS) systems have expanded language coverage, but their robustness under complex text inputs remains insufficiently diagnosed. Existing evaluations mainly focus on naturalness, speaker similarity, and content consistency using regular test sentences, while providing limited insight into how multilingual TTS systems fail when handling challenging inputs such as numbers, dates, named entities, long sentences, code-switched expressions, and punctuation-related structures. This paper proposes a complex-text robustness diagnosis framework for low-resource multilingual TTS. We evaluate robustness from three dimensions: content consistency, language consistency, and generation stability. A multilingual robustness testing scheme is designed for Thai, Vietnamese, Swahili, and Indonesian, covering ordinary sentences and multiple types of complex text inputs. We further introduce automatic diagnostic metrics, including character error rate, language identification accuracy, and duration abnormal rate. To support input-level risk analysis before speech generation, we propose a lightweight Text Risk Score (TRS), which estimates synthesis risk from interpretable text features without manual annotation or model training. Experiments on three representative multilingual TTS systems, including OmniVoice, VoxCPM2, and MMS-TTS, show that complex text inputs expose systematic failure patterns that are not fully reflected by ordinary short-sentence evaluation. Different systems exhibit distinct vulnerabilities in number normalization, named entity handling, long-text generation, and code-switched input processing. Furthermore, TRS shows a positive correlation with content errors and duration abnormalities, demonstrating its usefulness as a low-cost pre-synthesis indicator for complex-text risk diagnosis in low-resource multilingual TTS.

cs.CL↗

arXiv2026

SphereVAE: Hyperspherical Latent Autoencoders for Robust Autoregressive Speech Representation Modeling

With the rapid development of speech generation technology, discrete codec representations have been widely used because they provide a stable prediction paradigm. In expressive speech generation, however, the quantization bottleneck of discrete codecs results in information gaps in fine-grained prosody, timbre, pronunciation, and frame-to-frame continuity. Continuous representations (e.g., VAE latents), by eliminating this constraint, have emerged as a more effective alternative for autoregressive modeling. Yet when continuous representations are used as autoregressive prediction targets, prediction errors can accumulate along the generation chain, causing latent drift and degrading long-form stability. To mitigate this problem, we propose SphereVAE, which constrains the VAE latent space to the unit hypersphere. SphereVAE defines a Power Spherical posterior on the hypersphere and regularizes the latent distribution toward a uniform prior, so that information is encoded mainly by directional variation, providing a bounded geometric target for autoregressive prediction and reducing the risk of norm drift. SphereVAE underperforms the standard VAE on reconstruction metrics due to reduced latent freedom. However, when integrated into VoxCPM for zero-shot TTS and long-text generation, it yields lower content error rates with comparable speaker similarity, and shows more stable long-range speaker consistency. These results indicate that an appropriate latent geometric constraint can effectively mitigate autoregressive error accumulation and drift in speech generation.

eess.AS↗

arXiv2026

SpeechAnnotator: A Context-Aware Multi-Agent Framework and Benchmark for Multidimensional Speech Annotation

Recent controllable speech generation requires training data with fine-grained annotations of speaker traits, prosody, emotion, paralinguistic cues, acoustic scenes, and context. Existing workflows often rely on manual correction, paid hosted multimodal services, or fixed processing chains, which limits large-scale data processing through annotation cost, external-service dependence, or weak cross-stage recovery. We introduce SpeechAnnotator, a locally deployable, context-aware multi-agent framework built entirely from open-source models and tools. Supporting frontend modules first obtain speaker-aware segments and final segment transcripts, while prior evidence extractors attach heterogeneous segment-level cues. Three specialist agents then collaborate through shared state: the Planning Agent converts local audio evidence, speaker history, neighboring segments, and recording-level context into field-specific contracts; the Labeling Agent performs contract-guided multimodal prediction for directly observable attributes; and the Review Agent runs a bounded review loop that checks evidence support and cross-segment consistency, triggering relabeling only for unsupported or inconsistent fields. To address the fragmentation of existing evaluation resources across isolated tasks and narrow-domain test sets, we introduce SpeechAnnotator-Bench (SA-Bench), containing 8.87 hours of human-annotated audio across nine source formats, together with SpeechAnnotator-Eval (SA-Eval), which separates Timeline-Eval for speaker-aware timeline recovery, Closed-Eval for finite-set attributes, and Open-Eval for open-ended attributes. Experiments and ablations show that SpeechAnnotator provides a locally deployable alternative to commercial audio-capable systems, while the bounded review loop improves multidimensional annotation through evidence- and context-aware field-level recovery.

eess.AS↗

arXiv2026

Towards Fine-Grained Multi-Dimensional Speech Understanding: Data Pipeline, Benchmark, and Model

While speech Large Language Models (LLMs) excel at conventional tasks like basic speech recognition, they lack fine-grained, multi-dimensional perception. This deficiency is evident in their struggle to disentangle complex features like micro-acoustic cues, acoustic scenes, and paralinguistic signals. This resulting incomplete comprehension of real-world speech fundamentally bottlenecks the development of perceptive and empathetic next-generation speech systems. At its core, this persistent perceptual limitation primarily stems from three interacting factors: scarce high-quality expressive data, absent fine-grained modeling for multi-dimensional attributes, and reliance on restricted coverage, coarse-grained benchmarks. We address these challenges through three pillars: First, our robust data curation pipeline resolves complex acoustic environments and long-audio timestamp alignment challenges to extract a high-quality spontaneous speech corpus from audiovisual sources. Second, we construct FMSU-Bench, a pioneering benchmark covering 14 speech attribute dimensions to rigorously assess the fine-grained, multi-dimensional speech understanding capabilities of current models. Third, empowered by our curated corpus, we introduce FM-Speech. Driven by a decoupled attribute modeling and progressive curriculum fine-tuning framework, it substantially elevates fine-grained, multi-dimensional acoustic perception. Extensive evaluations on FMSU-Bench reveal that current speech LLMs still require significant improvement in multi-dimensional, fine-grained understanding. In contrast, FM-Speech substantially outperforms current open-source models, establishing a robust paradigm for real-world speech understanding.

eess.AS↗

arXiv2026

CNsEMD: An Expert-Annotated Multi-Field-Strength MRI Dataset and a Hyperspherical Manifold Network for Multimodal Cranial Nerve Parcellation

Cranial nerves (CNs) play essential roles in sensory, motor, and autonomic functions. Accurate CN parcellation from multimodal magnetic resonance imaging (MRI) is crucial for neuroanatomical analysis and neurosurgical planning. However, accurate CN parcellation remains extremely challenging because CNs are very small, exhibit low image contrast, and have slender tubular morphologies and complex anatomical trajectories. Moreover, the lack of publicly available, expert-annotated datasets has impeded the development and fair benchmarking of learning-based CN analysis methods. In this work, we introduce CNsEMD, an expert-annotated multimodal dataset for CN parcellation. It comprises data from 202 subjects acquired on 3T, 5T, and 7T MRI scanners. We further propose the projective hyperspherical manifold network (PHM-Net), which learns cross-modal representations by capturing angular relationships in a shared hyperspherical embedding space. Rather than performing multimodal fusion in Euclidean space, the proposed Hyperspherical cross-modal interaction (HCI) module enables bidirectional feature exchange between T1-weighted (T1w) and direction-encoded color (DEC) representations on a unit hypersphere. The Magnitude-preserving projective hyperspherical orientation representation (PHOR) captures the axial nature of DEC orientations while preserving diffusion magnitude. The hyperspherical prototype segmentation head (HPSH) further extends angular similarity to voxel-wise classification using normalized voxel embeddings and learnable class prototypes. Extensive experimental results on the CNsEMD dataset demonstrate the effectiveness of our PHM-Net against state-of-the-art methods. CNsEMD establishes a reproducible benchmark for multimodal CN imaging, while PHM-Net provides a geometry-consistent solution for CN parcellation across diverse MRI acquisitions.

cs.CV↗