arXiv subjects

Tianzi Wang

Publications and source records attributed to Tianzi Wang.

At least 19 recordsLinked to original sources

arXiv2026

Qwen-Audio-3.0-ASR Technical Report

In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling, model scaling, and deep integration with large language models (LLMs). However, bridging the gap between academic benchmark performance and real-world production utility remains a persistent challenge, particularly in handling diverse regional dialects, dynamic entities and hotwords, long-range contextual information, and disfluent spontaneous speech. In this report, we present Qwen-Audio-3.0-ASR, a Mixture-of-Experts (MoE) LLM-based ASR system designed to address these production demands through a unified, instruction-following framework. The model is built upon the Qwen backbone, and is trained on tens of millions of hours of large-scale speech data. Qwen-Audio-3.0-ASR supports transcription across 30 languages and 16 Chinese dialectal varieties spanning eight major dialect regions. Beyond multilingual and dialectal recognition, the model provides production-oriented capabilities including industry-domain entity recognition, hierarchical hotword customization, native single-pass transcription polishing, and long-audio contextual modeling. We further develop a dedicated streaming variant, Qwen-Audio-3.0-ASR-Streaming, for latency-sensitive applications. Extensive evaluations on Chinese, English, multilingual, and real-world industrial test sets demonstrate state-of-the-art or highly competitive recognition performance across a broad range of evaluation conditions, with strong performance relative to leading commercial and proprietary systems including GPT-4o Transcribe and Gemini 3.1 Pro.

cs.CL↗

arXiv2026

Decoding while Adapting: Zero-Shot Online Speaker Adaptation via Audio-Textual Prompts for Elderly Speech Recognition

This paper proposes a novel cross-utterance audio-textual prompts based speaker adaptation approach for elderly speech recognition. It enables zero-shot, real-time adaptation to unseen speakers. Speech and text embeddings are extracted from the current and a few preceding utterances, before being fused in a cross-modal manner to produce compact speaker prompts that are more consistent than i/x-vectors and ECAPA-TDNN features. Experiments on the English DementiaBank Pitt and Cantonese JCCOCC MoCA elderly speech datasets suggest that the proposed online adaptation outperforms the speaker-independent (SI) model by statistically significant word error rate (WER) or character error rate (CER) reductions of 0.61% and 1.22% absolute (2.99% and 4.48% relative). Real-time factor (RTF) speed-up ratios of up to 9.83 times are obtained over offline batch-mode adaptation.

eess.AS↗

arXiv2026

UNISON: A Unified Sound Generation and Editing Framework via Deep LLM Fusion

We present UNISON, a latent diffusion framework that unifies speech generation, sound generation, and audio editing within a single model. A single model handles text-to-audio, text-to-speech, zero-shot speaker cloning, mixed speech-and-sound generation, scene-level audio editing, speech-in-scene editing, and timed temporal composition, all of which share a single set of weights. Our architecture features two core designs: (1) Layer-wise deep LLM fusion, which injects hidden states from uniformly sampled layers of a frozen MLLM into corresponding MM-DiT blocks via learned projections, providing depth-matched semantic conditioning that improves instruction following over single-layer baselines; and (2) a unified multi-task architecture where task identity is encoded solely by a channel-wise mask and source audio is provided through VAE-encoded channel concatenation. Training is stabilized by an online GPU-side multi-task data synthesis pipeline with task-homogeneous batching and a two-stage curriculum. With 621M--732M trainable parameters, UNISON achieves results competitive with or exceeding task-specialist models across evaluated domains, while being roughly $4\times$ smaller than comparable unified systems.

eess.AS↗

arXiv2026

JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments

Current audio-visual large language models (AV-LLMs) are predominantly restricted to 2D perception, relying on RGB video and monaural audio. This design choice introduces a fundamental dimensionality mismatch that precludes reliable source localization and spatial reasoning in complex 3D environments. We address this limitation by presenting JAEGER, a framework that extends AV-LLMs to 3D space, to enable joint spatial grounding and reasoning through the integration of RGB-D observations and multi-channel first-order ambisonics. A core contribution of our work is the neural intensity vector (Neural IV), a learned spatial audio representation that encodes robust directional cues to enhance direction-of-arrival estimation, even in adverse acoustic scenarios with overlapping sources. To facilitate large-scale training and systematic evaluation, we propose SpatialSceneQA, a benchmark of 61k instruction-tuning samples curated from simulated physical environments. Extensive experiments demonstrate that our approach consistently surpasses 2D-centric baselines across diverse spatial perception and reasoning tasks, underscoring the necessity of explicit 3D modelling for advancing AI in physical environments. Our source code, pre-trained model checkpoints, and datasets are available at https://github.com/liuzhan22/JAEGER.

cs.CV↗

arXiv2026

MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks

While large audio-language models have advanced open-ended audio understanding, they still fall short of nuanced human-level comprehension. This gap persists largely because current benchmarks, limited by data annotations and evaluation metrics, fail to reliably distinguish between generic and highly detailed model outputs. To this end, this work introduces MECAT, a Multi-Expert Constructed Benchmark for Fine-Grained Audio Understanding Tasks. Generated via a pipeline that integrates analysis from specialized expert models with Chain-of-Thought large language model reasoning, MECAT provides multi-perspective, fine-grained captions and open-set question-answering pairs. The benchmark is complemented by a novel metric: DATE (Discriminative-Enhanced Audio Text Evaluation). This metric penalizes generic terms and rewards detailed descriptions by combining single-sample semantic similarity with cross-sample discriminability. A comprehensive evaluation of state-of-the-art audio models is also presented, providing new insights into their current capabilities and limitations. The data and code are available at https://github.com/xiaomi-research/mecat

eess.AS↗

arXiv2026

MiDashengLM: Efficient Audio Understanding with General Audio Captions

Current approaches for large audio language models (LALMs) often rely on closed data sources or proprietary models, limiting their generalization and accessibility. This paper introduces MiDashengLM, a novel open audio-language model designed for efficient and comprehensive audio understanding through the use of general audio captions using our novel ACAVCaps training dataset. MiDashengLM exclusively relies on publicly available pretraining and supervised fine-tuning (SFT) datasets, ensuring full transparency and reproducibility. At its core, MiDashengLM integrates Dasheng, an open-source audio encoder, specifically engineered to process diverse auditory information effectively. Unlike previous works primarily focused on Automatic Speech Recognition (ASR) based audio-text alignment, our strategy centers on general audio captions, fusing speech, sound and music information into one textual representation, enabling a holistic textual representation of complex audio scenes. Lastly, MiDashengLM provides an up to 4x speedup in terms of time-to-first-token (TTFT) and up to 20x higher throughput than comparable models. Checkpoints are available online at https://huggingface.co/mispeech/midashenglm-7b and https://github.com/xiaomi-research/dasheng-lm.

cs.SD↗

arXiv2026

ACAVCaps: Enabling large-scale training for fine-grained and diverse audio understanding

General audio understanding is a fundamental goal for large audio-language models, with audio captioning serving as a cornerstone task for their development. However, progress in this domain is hindered by existing datasets, which lack the scale and descriptive granularity required to train truly versatile models. To address this gap, we introduce ACAVCaps, a new large-scale, fine-grained, and multi-faceted audio captioning dataset. Derived from the ACAV100M collection, ACAVCaps is constructed using a multi-expert pipeline that analyzes audio from diverse perspectives-including speech, music, and acoustic properties-which are then synthesized into rich, detailed descriptions by a large language model. Experimental results demonstrate that models pre-trained on ACAVCaps exhibit substantially stronger generalization capabilities on various downstream tasks compared to those trained on other leading captioning datasets. The dataset is available at https://github.com/xiaomi-research/acavcaps.

eess.AS↗

arXiv2026

The immediate effect of kangaroo mother care on Mother-infant inter-brain synchrony and infant brain function

Kangaroo mother care (KMC) is an intervention involving skin-to-skin contact that promotes physiological stability and supports long-term neurodevelopment in preterm infants. However, the underlying neurophysiological mechanisms remain unclear. We aimed to investigate the immediate effects of the first KMC on infants' brain function, mother-infant inter-brain synchrony, as well as their associations. Fifty-eight preterm infants (gestational age < 32 weeks or birth weight < 1500 g) and their mothers underwent synchronous dual-electroencephalography recording before and during the first KMC session. Infant brain function was assessed via power spectrum energy and graph theory-based network metrics, and mother-infant inter-brain synchrony was quantified using phase-locking value (PLV), from which inter-brain density and inter-brain strength were calculated. Correlation analyses were performed between infant intra-brain metrics and inter-brain synchrony indicators.During the first KMC, preterm infants showed enhanced theta, alpha, and beta power alongside reduced relative delta power, while brain network topological metrics remained stable. Concurrently, mother-infant inter-brain synchrony was significantly enhanced across all frequency bands, as evidenced by increased inter-brain density and strength (all p < .001). Furthermore, in the alpha band, inter-brain strength correlated positively with infant local efficiency and clustering coefficient, and in the beta band, it was positively correlated with infant small-worldness. The first KMC session can immediately enhance both preterm infant single-brain activity and mother-infant inter-brain synchrony. The strength of inter-brain synchrony is associated with the infant's intra-brain network organization, suggesting that KMC may promote intra-brain development in preterm infants via enhancing mother-infant inter-brain synchrony.

q-bio.NC↗

arXiv2026

GLAP: General contrastive audio-text pretraining across domains and languages

Contrastive Language Audio Pretraining (CLAP) is a widely-used method to bridge the gap between audio and text domains. Current CLAP methods enable sound and music retrieval in English, ignoring multilingual spoken content. To address this, we introduce general language audio pretraining (GLAP), which expands CLAP with multilingual and multi-domain abilities. GLAP demonstrates its versatility by achieving competitive performance on standard audio-text retrieval benchmarks like Clotho and AudioCaps, while significantly surpassing existing methods in speech retrieval and classification tasks. Additionally, GLAP achieves strong results on widely used sound-event zero-shot benchmarks, while simultaneously outperforming previous methods on speech content benchmarks. Further keyword spotting evaluations across 50 languages emphasize GLAP's advanced multilingual capabilities. Finally, multilingual sound and music understanding is evaluated across four languages. Checkpoints and Source: https://github.com/xiaomi-research/dasheng-glap.

cs.SD↗

arXiv2025

AzeroS: Extending LLM to Speech with Self-Generated Instruction-Free Tuning

Extending large language models (LLMs) to the speech domain has recently gained significant attention. A typical approach connects a pretrained LLM with an audio encoder through a projection module and trains the resulting model on large-scale, task-specific instruction-tuning datasets. However, curating such instruction-tuning data for specific requirements is time-consuming, and models trained in this manner often generalize poorly to unseen tasks. In this work, we first formulate that the strongest generalization of a speech-LLM is achieved when it is trained with Self-Generated Instruction-Free Tuning (SIFT), in which supervision signals are generated by a frozen LLM using textual representations of speech as input. Our proposed SIFT paradigm eliminates the need for collecting task-specific question-answer pairs and yields the theoretically best generalization to unseen tasks. Building upon this paradigm, we introduce AZeroS (Auden Zero-instruction-tuned Speech-LLM), which is trained on speech-text pairs derived from publicly available corpora, including approximately 25,000 hours of speech with ASR transcripts and 3,000 hours of speech with paralinguistic labels. Built upon Qwen2.5-7B-Instruct, the model updates only two lightweight projection modules (23.8 million parameters each), while keeping both the LLM and audio encoders frozen. Despite the minimal training cost and modest data scale, AZeroS achieves state-of-the-art performance on both semantic and paralinguistic benchmarks, including VoiceBench, AIR-Bench Foundation (Speech), and AIR-Bench Chat (Speech).

cs.CL↗

arXiv2025

Towards Effective and Efficient Non-autoregressive decoders for Conformer and LLM-based ASR using Block-based Attention Mask

Automatic speech recognition (ASR) systems often rely on autoregressive (AR) Transformer decoder architectures, which limit efficient inference parallelization due to their sequential nature. To this end, non-autoregressive (NAR) approaches aim primarily to achieve significant decoding speedup while the maintaining recognition accuracy that is comparable to AR baselines. This paper proposes a novel NAR block-based attention mask decoder (AMD) that effectively improves decoding efficiency while maintaining ASR accuracy, and also offering flexibility in balancing the performance-efficiency trade-off on both Conformer and large language model (LLM)-based ASR systems. The proposed AMD performs parallel inference within contiguous blocks of output labels while maintaining monotonic left-to-right prediction between blocks. A one-pass beam search algorithm is designed to dynamically fuse Connectionist Temporal Classification (CTC), AR decoder, and AMD probabilities. Experiments are conducted on normal speech LS960 and DBank elderly speech across: a) The Conformer encoder-decoder ASR system with filterbank input features; b) its integration with WavLM features; and c) further advancement by integrating an LLM-based decoder. On the LS960 task, the proposed AMD empowered tripartite decoder achieves decoding speedup ratios of up to 1.44x, 1.55x, and 2.31x under the three model configurations over the CTC + AR baselines, without statistically significant WER increases. When operating with real-time factors (RTFs) comparable to the baselines, the tripartite decoder produces statistically significant WER reductions of 0.19%, 0.62% and 0.13% absolute (4.3%, 16.3%, and 3.8% relative). Similar improvements are also obtained on the DBank task.

eess.AS↗

arXiv2025

Exploring Cross-Utterance Speech Contexts for Conformer-Transducer Speech Recognition Systems

This paper investigates four types of cross-utterance speech contexts modeling approaches for streaming and non-streaming Conformer-Transformer (C-T) ASR systems: i) input audio feature concatenation; ii) cross-utterance Encoder embedding concatenation; iii) cross-utterance Encoder embedding pooling projection; or iv) a novel chunk-based approach applied to C-T models for the first time. An efficient batch-training scheme is proposed for contextual C-Ts that uses spliced speech utterances within each minibatch to minimize the synchronization overhead while preserving the sequential order of cross-utterance speech contexts. Experiments are conducted on four benchmark speech datasets across three languages: the English GigaSpeech and Mandarin Wenetspeech corpora used in contextual C-T models pre-training; and the English DementiaBank Pitt and Cantonese JCCOCC MoCA elderly speech datasets used in domain fine-tuning. The best performing contextual C-T systems consistently outperform their respective baselines using no cross-utterance speech contexts in pre-training and fine-tuning stages with statistically significant average word error rate (WER) or character error rate (CER) reductions up to 0.9%, 1.1%, 0.51%, and 0.98% absolute (6.0%, 5.4%, 2.0%, and 3.4% relative) on the four tasks respectively. Their performance competitiveness against Wav2vec2.0-Conformer, XLSR-128, and Whisper models highlights the potential benefit of incorporating cross-utterance speech contexts into current speech foundation models.

eess.AS↗

arXiv2025

Exploring SSL Discrete Speech Features for Zipformer-based Contextual ASR

Self-supervised learning (SSL) based discrete speech representations are highly compact and domain adaptable. In this paper, SSL discrete speech features extracted from WavLM models are used as additional cross-utterance acoustic context features in Zipformer-Transducer ASR systems. The efficacy of replacing Fbank features with discrete token features for modelling either cross-utterance contexts (from preceding and future segments), or current utterance's internal contexts alone, or both at the same time, are demonstrated thoroughly on the Gigaspeech 1000-hr corpus. The best Zipformer-Transducer system using discrete tokens based cross-utterance context features outperforms the baseline using utterance internal context only with statistically significant word error rate (WER) reductions of 0.32% to 0.41% absolute (2.78% to 3.54% relative) on the dev and test data. The lowest published WER of 11.15% and 11.14% were obtained on the dev and test sets. Our work is open-source and publicly available at https://github.com/open-creator/icefall/tree/master/egs/gigaspeech/Context\_ASR.

cs.CL↗

arXiv2025

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition

This paper proposes a novel MoE-based speaker adaptation framework for foundation models based dysarthric speech recognition. This approach enables zero-shot adaptation and real-time processing while incorporating domain knowledge. Speech impairment severity and gender conditioned adapter experts are dynamically combined using on-the-fly predicted speaker-dependent routing parameters. KL-divergence is used to further enforce diversity among experts and their generalization to unseen speakers. Experimental results on the UASpeech corpus suggest that on-the-fly MoE-based adaptation produces statistically significant WER reductions of up to 1.34% absolute (6.36% relative) over the unadapted baseline HuBERT/WavLM models. Consistent WER reductions of up to 2.55% absolute (11.44% relative) and RTF speedups of up to 7 times are obtained over batch-mode adaptation across varying speaker-level data quantities. The lowest published WER of 16.35% (46.77% on very low intelligibility) is obtained.

cs.SD↗

arXiv2025

Unfolding A Few Structures for The Many: Memory-Efficient Compression of Conformer and Speech Foundation Models

This paper presents a novel memory-efficient model compression approach for Conformer ASR and speech foundation systems. Our approach features a unique "small-to-large" design. A compact "seed" model containing a few Conformer or Transformer blocks is trained and unfolded many times to emulate the performance of larger uncompressed models with different logical depths. The seed model and many unfolded paths are jointly trained within a single unfolding cycle. The KL-divergence between the largest unfolded and smallest seed models is used in a self-distillation process to minimize their performance disparity. Experimental results show that our foldable model produces ASR performance comparable to individually constructed Conformer and wav2vec2/HuBERT speech foundation models under various depth configurations, while requiring only minimal memory and storage. Conformer and wav2vec2 models with a reduction of 35% and 30% parameters are obtained without loss of performance, respectively.

cs.SD↗

arXiv2025

Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision

Model compression has become an emerging need as the sizes of modern speech systems rapidly increase. In this paper, we study model weight quantization, which directly reduces the memory footprint to accommodate computationally resource-constrained applications. We propose novel approaches to perform extremely low-bit (i.e., 2-bit and 1-bit) quantization of Conformer automatic speech recognition systems using multiple precision model co-training, stochastic precision, and tensor-wise learnable scaling factors to alleviate quantization incurred performance loss. The proposed methods can achieve performance-lossless 2-bit and 1-bit quantization of Conformer ASR systems trained with the 300-hr Switchboard and 960-hr LibriSpeech corpus. Maximum overall performance-lossless compression ratios of 16.2 and 16.6 times are achieved without a statistically significant increase in the word error rate (WER) over the full precision baseline systems, respectively.

cs.SD↗

arXiv2025

Frequency super-resolution with quantum environment engineering in a weakly coupled nuclear-spin system

Optical super-resolution has been widely employed to beat spatial diffraction limit, which is often stated by Abbe-Rayleigh criterion. Analogously, we propose a frequency super-resolution method, which beats conventional spectral resolution limit often approximated by full width half maximum of the spectral peak, Γ. This method utilizes recently developed quantum environment engineering technique. With numerical simulations and experiments, we demonstrate the frequency super-resolution method in a three-nuclear-spin system (Trifluoroiodoethylene), by successfully decomposing a thermal state spectrum of the spin F3 into four peaks of engineered pseudo-pure states of the quantum environment. The ultimate frequency resolution reaches {\sim} 0.005 Γ. This method is potentially useful in spectral decomposition of weakly coupled nuclear spin systems and might be improved further to acquire finer frequency super-resolution by employing more advanced quantum techniques..

quant-ph↗

arXiv2024

Structured Speaker-Deficiency Adaptation of Foundation Models for Dysarthric and Elderly Speech Recognition

Data-intensive fine-tuning of speech foundation models (SFMs) to scarce and diverse dysarthric and elderly speech leads to data bias and poor generalization to unseen speakers. This paper proposes novel structured speaker-deficiency adaptation approaches for SSL pre-trained SFMs on such data. Speaker and speech deficiency invariant SFMs were constructed in their supervised adaptive fine-tuning stage to reduce undue bias to training data speakers, and serves as a more neutral and robust starting point for test time unsupervised adaptation. Speech variability attributed to speaker identity and speech impairment severity, or aging induced neurocognitive decline, are modelled using separate adapters that can be combined together to model any seen or unseen speaker. Experiments on the UASpeech dysarthric and DementiaBank Pitt elderly speech corpora suggest structured speaker-deficiency adaptation of HuBERT and Wav2vec2-conformer models consistently outperforms baseline SFMs using either: a) no adapters; b) global adapters shared among all speakers; or c) single attribute adapters modelling speaker or deficiency labels alone by statistically significant WER reductions up to 3.01% and 1.50% absolute (10.86% and 6.94% relative) on the two tasks respectively. The lowest published WER of 19.45% (49.34% on very low intelligibility, 33.17% on unseen words) is obtained on the UASpeech test set of 16 dysarthric speakers.

eess.AS↗