arXiv subjects

Xixin Wu

Publications and source records attributed to Xixin Wu.

At least 37 records · Page 2Linked to original sources

arXiv2025

Bridging the gap between training and inference in LM-based TTS models

Recent advancements in text-to-speech (TTS) have shown that language model (LM) based systems offer competitive performance compared to traditional approaches. However, in training, TTS models use ground-truth (GT) tokens as prefixes to predict the next token, while in inference these tokens are not available, a gap between training and inference that is often neglected. In this study, we propose a prompt-guided hybrid training scheme to mitigate exposure bias in popular LM-based TTS systems. Our core idea is to adopt a hybrid training paradigm that combines teacher forcing with free running, thereby introducing self-generated tokens into the training process. This makes the training mode more consistent with inference, reducing the training-inference gap. In addition, we incorporate an EOS prediction mechanism during training to detect incorrect sequence termination and adaptively control the free running process. Experimental results provide a comprehensive evaluation of the impact of exposure bias on LM-based TTS, and demonstrate that our method effectively narrows the training-inference gap, thereby improving the quality of synthesized long-form speech.

cs.SD↗

arXiv2025

Seamless Language Expansion: Enhancing Multilingual Mastery in Self-Supervised Models

Self-supervised (SSL) models have shown great performance in various downstream tasks. However, they are typically developed for limited languages, and may encounter new languages in real-world. Developing a SSL model for each new language is costly. Thus, it is vital to figure out how to efficiently adapt existed SSL models to a new language without impairing its original abilities. We propose adaptation methods which integrate LoRA to existed SSL models to extend new language. We also develop preservation strategies which include data combination and re-clustering to retain abilities on existed languages. Applied to mHuBERT, we investigate their effectiveness on speech re-synthesis task. Experiments show that our adaptation methods enable mHuBERT to be applied to a new language (Mandarin) with MOS value increased about 1.6 and the relative value of WER reduced up to 61.72%. Also, our preservation strategies ensure that the performance on both existed and new languages remains intact.

cs.CL↗

arXiv2025

Incorporating Linguistic Constraints from External Knowledge Source for Audio-Visual Target Speech Extraction

Audio-visual target speaker extraction (AV-TSE) models primarily rely on target visual cues to isolate the target speaker's voice from others. We know that humans leverage linguistic knowledge, such as syntax and semantics, to support speech perception. Inspired by this, we explore the potential of pre-trained speech-language models (PSLMs) and pre-trained language models (PLMs) as auxiliary knowledge sources for AV-TSE. In this study, we propose incorporating the linguistic constraints from PSLMs or PLMs for the AV-TSE model as additional supervision signals. Without introducing any extra computational cost during inference, the proposed approach consistently improves speech quality and intelligibility. Furthermore, we evaluate our method in multi-language settings and visual cue-impaired scenarios and show robust performance gains.

cs.SD↗

arXiv2025

Naturalistic Language-related Movie-Watching fMRI Task for Detecting Neurocognitive Decline and Disorder

Early detection is crucial for timely intervention aimed at preventing and slowing the progression of neurocognitive disorder (NCD), a common and significant health problem among the aging population. Recent evidence has suggested that language-related functional magnetic resonance imaging (fMRI) may be a promising approach for detecting cognitive decline and early NCD. In this paper, we proposed a novel, naturalistic language-related fMRI task for this purpose. We examined the effectiveness of this task among 97 non-demented Chinese older adults from Hong Kong. The results showed that machine-learning classification models based on fMRI features extracted from the task and demographics (age, gender, and education year) achieved an average area under the curve of 0.86 when classifying participants' cognitive status (labeled as NORMAL vs DECLINE based on their scores on a standard neurcognitive test). Feature localization revealed that the fMRI features most frequently selected by the data-driven approach came primarily from brain regions associated with language processing, such as the superior temporal gyrus, middle temporal gyrus, and right cerebellum. The study demonstrated the potential of the naturalistic language-related fMRI task for early detection of aging-related cognitive decline and NCD.

cs.CL↗

arXiv2025

WAKE: Watermarking Audio with Key Enrichment

As deep learning advances in audio generation, challenges in audio security and copyright protection highlight the need for robust audio watermarking. Recent neural network-based methods have made progress but still face three main issues: preventing unauthorized access, decoding initial watermarks after multiple embeddings, and embedding varying lengths of watermarks. To address these issues, we propose WAKE, the first key-controllable audio watermark framework. WAKE embeds watermarks using specific keys and recovers them with corresponding keys, enhancing security by making incorrect key decoding impossible. It also resolves the overwriting issue by allowing watermark decoding after multiple embeddings and supports variable-length watermark insertion. WAKE outperforms existing models in both watermarked audio quality and watermark detection accuracy. Code, more results, and demo page: https://thuhcsi.github.io/WAKE.

cs.SD↗

arXiv2025

DiffDSR: Dysarthric Speech Reconstruction Using Latent Diffusion Model

Dysarthric speech reconstruction (DSR) aims to convert dysarthric speech into comprehensible speech while maintaining the speaker's identity. Despite significant advancements, existing methods often struggle with low speech intelligibility and poor speaker similarity. In this study, we introduce a novel diffusion-based DSR system that leverages a latent diffusion model to enhance the quality of speech reconstruction. Our model comprises: (i) a speech content encoder for phoneme embedding restoration via pre-trained self-supervised learning (SSL) speech foundation models; (ii) a speaker identity encoder for speaker-aware identity preservation by in-context learning mechanism; (iii) a diffusion-based speech generator to reconstruct the speech based on the restored phoneme embedding and preserved speaker identity. Through evaluations on the widely-used UASpeech corpus, our proposed model shows notable enhancements in speech intelligibility and speaker similarity.

cs.SD↗

arXiv2025

RAG-Zeval: Towards Robust and Interpretable Evaluation on RAG Responses through End-to-End Rule-Guided Reasoning

Robust evaluation is critical for deploying trustworthy retrieval-augmented generation (RAG) systems. However, current LLM-based evaluation frameworks predominantly rely on directly prompting resource-intensive models with complex multi-stage prompts, underutilizing models' reasoning capabilities and introducing significant computational cost. In this paper, we present RAG-Zeval (RAG-Zero Evaluator), a novel end-to-end framework that formulates faithfulness and correctness evaluation as a rule-guided reasoning task. Our approach trains evaluators with reinforcement learning, facilitating compact models to generate comprehensive and sound assessments with detailed explanation in one-pass. We introduce a ranking-based outcome reward mechanism, using preference judgments rather than absolute scores, to address the challenge of obtaining precise pointwise reward signals. To this end, we synthesize the ranking references by generating quality-controlled responses with zero human annotation. Experiments demonstrate RAG-Zeval's superior performance, achieving the strongest correlation with human judgments and outperforming baselines that rely on LLMs with 10-100 times more parameters. Our approach also exhibits superior interpretability in response evaluation.

cs.CL↗

arXiv2025

Autoregressive Speech Synthesis without Vector Quantization

We present MELLE, a novel continuous-valued token based language modeling approach for text-to-speech synthesis (TTS). MELLE autoregressively generates continuous mel-spectrogram frames directly from text condition, bypassing the need for vector quantization, which is typically designed for audio compression and sacrifices fidelity compared to continuous representations. Specifically, (i) instead of cross-entropy loss, we apply regression loss with a proposed spectrogram flux loss function to model the probability distribution of the continuous-valued tokens; (ii) we have incorporated variational inference into MELLE to facilitate sampling mechanisms, thereby enhancing the output diversity and model robustness. Experiments demonstrate that, compared to the two-stage codec language model VALL-E and its variants, the single-stage MELLE mitigates robustness issues by avoiding the inherent flaws of sampling vector-quantized codes, achieves superior performance across multiple metrics, and, most importantly, offers a more streamlined paradigm. The demos of our work are provided at https://aka.ms/melle.

cs.CL↗

arXiv2025

Enhancing Generalization of Speech Large Language Models with Multi-Task Behavior Imitation and Speech-Text Interleaving

Large language models (LLMs) have shown remarkable generalization across tasks, leading to increased interest in integrating speech with LLMs. These speech LLMs (SLLMs) typically use supervised fine-tuning to align speech with text-based LLMs. However, the lack of annotated speech data across a wide range of tasks hinders alignment efficiency, resulting in poor generalization. To address these issues, we propose a novel multi-task 'behavior imitation' method with speech-text interleaving, called MTBI, which relies solely on paired speech and transcripts. By ensuring the LLM decoder generates equivalent responses to paired speech and text, we achieve a more generalized SLLM. Interleaving is used to further enhance alignment efficiency. We introduce a simple benchmark to evaluate prompt and task generalization across different models. Experimental results demonstrate that our MTBI outperforms SOTA SLLMs on both prompt and task generalization, while requiring less supervised speech data.

eess.AS↗

arXiv2025

ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling

Recent advancements in audio language models have underscored the pivotal role of audio tokenization, which converts audio signals into discrete tokens, thereby facilitating the application of language model architectures to the audio domain. In this study, we introduce ALMTokenizer, a novel low-bitrate and semantically rich audio codec tokenizer for audio language models. Prior methods, such as Encodec, typically encode individual audio frames into discrete tokens without considering the use of context information across frames. Unlike these methods, we introduce a novel query-based compression strategy to capture holistic information with a set of learnable query tokens by explicitly modeling the context information across frames. This design not only enables the codec model to capture more semantic information but also encodes the audio signal with fewer token sequences. Additionally, to enhance the semantic information in audio codec models, we introduce the following: (1) A masked autoencoder (MAE) loss, (2) Vector quantization based on semantic priors, and (3) An autoregressive (AR) prediction loss. As a result, ALMTokenizer achieves competitive reconstruction performance relative to state-of-the-art approaches while operating at a lower bitrate. Within the same audio language model framework, ALMTokenizer outperforms previous tokenizers in audio understanding and generation tasks.

cs.SD↗

arXiv2025

Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions

Recent advancements in large language models (LLMs) have revolutionized various domains, bringing significant progress and new opportunities. Despite progress in speech-related tasks, LLMs have not been sufficiently explored in multi-talker scenarios. In this work, we present a pioneering effort to investigate the capability of LLMs in transcribing speech in multi-talker environments, following versatile instructions related to multi-talker automatic speech recognition (ASR), target talker ASR, and ASR based on specific talker attributes such as sex, occurrence order, language, and keyword spoken. Our approach utilizes WavLM and Whisper encoder to extract multi-faceted speech representations that are sensitive to speaker characteristics and semantic context. These representations are then fed into an LLM fine-tuned using LoRA, enabling the capabilities for speech comprehension and transcription. Comprehensive experiments reveal the promising performance of our proposed system, MT-LLM, in cocktail party scenarios, highlighting the potential of LLM to handle speech-related tasks based on user instructions in such complex settings. The code, model, and samples are available at https://github.com/cuhealthybrains/MT-LLM.

cs.CL↗

arXiv2025

$C^2$AV-TSE: Context and Confidence-aware Audio Visual Target Speaker Extraction

Audio-Visual Target Speaker Extraction (AV-TSE) aims to mimic the human ability to enhance auditory perception using visual cues. Although numerous models have been proposed recently, most of them estimate target signals by primarily relying on local dependencies within acoustic features, underutilizing the human-like capacity to infer unclear parts of speech through contextual information. This limitation results in not only suboptimal performance but also inconsistent extraction quality across the utterance, with some segments exhibiting poor quality or inadequate suppression of interfering speakers. To close this gap, we propose a model-agnostic strategy called the Mask-And-Recover (MAR). It integrates both inter- and intra-modality contextual correlations to enable global inference within extraction modules. Additionally, to better target challenging parts within each sample, we introduce a Fine-grained Confidence Score (FCS) model to assess extraction quality and guide extraction modules to emphasize improvement on low-quality segments. To validate the effectiveness of our proposed model-agnostic training paradigm, six popular AV-TSE backbones were adopted for evaluation on the VoxCeleb2 dataset, demonstrating consistent performance improvements across various metrics.

cs.SD↗

arXiv2025

AudioComposer: Towards Fine-grained Audio Generation with Natural Language Descriptions

Current Text-to-audio (TTA) models mainly use coarse text descriptions as inputs to generate audio, which hinders models from generating audio with fine-grained control of content and style. Some studies try to improve the granularity by incorporating additional frame-level conditions or control networks. However, this usually leads to complex system design and difficulties due to the requirement for reference frame-level conditions. To address these challenges, we propose AudioComposer, a novel TTA generation framework that relies solely on natural language descriptions (NLDs) to provide both content specification and style control information. To further enhance audio generative modeling, we employ flow-based diffusion transformers with the cross-attention mechanism to incorporate text descriptions effectively into audio generation processes, which can not only simultaneously consider the content and style information in the text inputs, but also accelerate generation compared to other architectures. Furthermore, we propose a novel and comprehensive automatic data simulation pipeline to construct data with fine-grained text descriptions, which significantly alleviates the problem of data scarcity in the area. Experiments demonstrate the effectiveness of our framework using solely NLDs as inputs for content specification and style control. The generation quality and controllability surpass state-of-the-art TTA models, even with a smaller model size.

eess.AS↗

arXiv2025

UniSep: Universal Target Audio Separation with Language Models at Scale

We propose Universal target audio Separation (UniSep), addressing the separation task on arbitrary mixtures of different types of audio. Distinguished from previous studies, UniSep is performed on unlimited source domains and unlimited source numbers. We formulate the separation task as a sequence-to-sequence problem, and a large language model (LLM) is used to model the audio sequence in the discrete latent space, leveraging the power of LLM in handling complex mixture audios with large-scale data. Moreover, a novel pre-training strategy is proposed to utilize audio-only data, which reduces the efforts of large-scale data simulation and enhances the ability of LLMs to understand the consistency and correlation of information within audio sequences. We also demonstrate the effectiveness of scaling datasets in an audio separation task: we use large-scale data (36.5k hours), including speech, music, and sound, to train a universal target audio separation model that is not limited to a specific domain. Experiments show that UniSep achieves competitive subjective and objective evaluation results compared with single-task models.

cs.SD↗

arXiv2025

CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction

Universal sound separation (USS) aims to extract arbitrary types of sounds from real-world recordings. This can be achieved by language-queried target sound extraction (TSE), which typically consists of two components: a query network that converts user queries into conditional embeddings, and a separation network that extracts the target sound accordingly. Existing methods commonly train models from scratch. As a consequence, substantial data and computational resources are required to make the randomly initialized model comprehend sound events and perform separation accordingly. In this paper, we propose to integrate pre-trained models into TSE models to address the above issue. To be specific, we tailor and adapt the powerful contrastive language-audio pre-trained model (CLAP) for USS, denoted as CLAPSep. CLAPSep also accepts flexible user inputs, taking both positive and negative user prompts of uni- and/or multi-modalities for target sound extraction. These key features of CLAPSep can not only enhance the extraction performance but also improve the versatility of its application. We provide extensive experiments on 5 diverse datasets to demonstrate the superior performance and zero- and few-shot generalizability of our proposed CLAPSep with fast training convergence, surpassing previous methods by a significant margin. Full codes and some audio examples are released for reproduction and evaluation.

eess.AS↗

arXiv2025

Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution

Improving context faithfulness in large language models is essential for developing trustworthy retrieval augmented generation systems and mitigating hallucinations, especially in long-form question answering (LFQA) tasks or scenarios involving knowledge conflicts. Existing methods either intervene LLMs only at inference without addressing their inherent limitations or overlook the potential for self-improvement. In this paper, we introduce GenDiE (Generate, Discriminate, Evolve), a novel self-evolving framework that enhances context faithfulness through fine-grained sentence-level optimization. GenDiE combines both generative and discriminative training, equipping LLMs with self-generation and self-scoring capabilities to facilitate iterative self-evolution. This supports both data construction for model alignment and score-guided search during inference. Furthermore, by treating each sentence in a response as an independent optimization unit, GenDiE effectively addresses the limitations of previous approaches that optimize at the holistic answer level, which may miss unfaithful details. Experiments on ASQA (in-domain LFQA) and ConFiQA (out-of-domain counterfactual QA) datasets demonstrate that GenDiE surpasses various baselines in both faithfulness and correctness, and exhibits robust performance for domain adaptation.

cs.CL↗

arXiv2025

Leveraging Chain of Thought towards Empathetic Spoken Dialogue without Corresponding Question-Answering Data

Empathetic dialogue is crucial for natural human-computer interaction, allowing the dialogue system to respond in a more personalized and emotionally aware manner, improving user satisfaction and engagement. The emergence of large language models (LLMs) has revolutionized dialogue generation by harnessing their powerful capabilities and shown its potential in multimodal domains. Many studies have integrated speech with text-based LLMs to take speech question as input and output text response. However, the lack of spoken question-answering datasets that include speech style information to supervised fine-tuning (SFT) limits the performance of these systems. As a result, while these systems excel at understanding speech content, they often struggle to generate empathetic responses. In response, we propose a novel approach that circumvents the need for question-answering data, called Listen, Perceive, and Express (LPE). Our method employs a two-stage training process, initially guiding the LLM to listen the content and perceive the emotional aspects of speech. Subsequently, we utilize Chain-of-Thought (CoT) prompting to unlock the model's potential for expressing empathetic responses based on listened spoken content and perceived emotional cues. We employ experiments to prove the effectiveness of proposed method. To our knowledge, this is the first attempt to leverage CoT for speech-based dialogue.

cs.CL↗

arXiv2025

DrawSpeech: Expressive Speech Synthesis Using Prosodic Sketches as Control Conditions

Controlling text-to-speech (TTS) systems to synthesize speech with the prosodic characteristics expected by users has attracted much attention. To achieve controllability, current studies focus on two main directions: (1) using reference speech as prosody prompt to guide speech synthesis, and (2) using natural language descriptions to control the generation process. However, finding reference speech that exactly contains the prosody that users want to synthesize takes a lot of effort. Description-based guidance in TTS systems can only determine the overall prosody, which has difficulty in achieving fine-grained prosody control over the synthesized speech. In this paper, we propose DrawSpeech, a sketch-conditioned diffusion model capable of generating speech based on any prosody sketches drawn by users. Specifically, the prosody sketches are fed to DrawSpeech to provide a rough indication of the expected prosody trends. DrawSpeech then recovers the detailed pitch and energy contours based on the coarse sketches and synthesizes the desired speech. Experimental results show that DrawSpeech can generate speech with a wide variety of prosody and can precisely control the fine-grained prosody in a user-friendly manner. Our implementation and audio samples are publicly available.

cs.SD↗