SEARCH · Search arXiv

Search Search arXiv

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

81 recordsLinked to original sources

arXiv2026

Advancing LLM-based phoneme-to-grapheme for multilingual speech recognition

Phoneme-based ASR factorizes recognition into speech-to-phoneme (S2P) and phoneme-to-grapheme (P2G), enabling cross-lingual acoustic sharing while keeping language-specific orthography in a separate module. While large language models (LLMs) are promising for P2G, multilingual P2G remains challenging due to language-aware generation and severe cross-language data imbalance. We study multilingual LLM-based P2G on the ten-language CV-Lang10 benchmark. We examine robustness strategies that account for S2P uncertainty, including DANP and Simplified SKM (S-SKM). S-SKM is a Monte Carlo approximation that avoids CTC-based S2P probability weighting in P2G training. Robust training and low-resource oversampling reduce the average WER from 10.56% to 7.66%.

eess.AS↗

arXiv2026

When Text Misleads: Inconsistent-Aware Reasoning for Audio-Grounded Dialogue

Understanding spoken dialogue requires joint reasoning over lexical content and paralinguistic acoustic signals such as emotion and conversational intent. However, existing evaluations often allow shortcuts based on transcripts or single-modality solutions, obscuring whether models genuinely ground predictions in speech. We formalize this failure mode as cross-modal disagreement, where transcripts suggest plausible but incorrect surface interpretations while acoustic cues such as prosody or speaking style support different answers. We develop a scalable framework that identifies text-biased surface interpretations and converts disagreement regions into conflict QA examples. We also include consistent cases where transcript-based and speech-grounded interpretations agree, enabling evaluation beyond adversarial audio dependence. This results in ContraTalk, a controlled benchmark containing 501 questions across five discourse dimensions: interaction behavior, emotion state, dialogue act, social stance, and conversational intent. We further develop an agentic-style reasoning framework that converts speech into an Audio Twin, a text-readable representation of localized acoustic cues that exposes acoustic evidence to the reasoning model. Experiments show that strong text-only LLMs exceed 90% accuracy in consistent cases but drop to 33-48% in conflict cases. Direct AudioLLMs provide only partial grounding, still selecting the transcript-biased trap in roughly 30-40% of conflict cases. Our Audio Twin framework improves conflict-case accuracy while reducing trap selection, but its consistent-case behavior remains backbone-dependent. These results identify transcript-based shortcuts as an important failure mode in spoken dialogue understanding and show that explicit acoustic evidence aggregation provides a more controllable interface for diagnosing and improving speech-grounded reasoning.

cs.CL↗

arXiv2026

DOTA-ME-CS: Daily Oriented Text Audio-Mandarin English-Code Switching Dataset

Code-switching, the alternation between two or more languages within communication, poses great challenges for Automatic Speech Recognition (ASR) systems. Existing models and datasets are limited in their ability to effectively handle these challenges. To address this gap and foster progress in code-switching ASR research, we introduce the DOTA-ME-CS: Daily oriented text audio Mandarin-English code-switching dataset, which consists of 18.54 hours of audio data, including 9,300 recordings from 34 participants. To enhance the dataset's diversity, we apply artificial intelligence (AI) techniques such as AI timbre synthesis, speed variation, and noise addition, thereby increasing the complexity and scalability of the task. The dataset is carefully curated to ensure both diversity and quality, providing a robust resource for researchers addressing the intricacies of bilingual speech recognition with detailed data analysis. We further demonstrate the dataset's potential in future research. The DOTA-ME-CS dataset, along with accompanying code are shared in the Github.

cs.SD↗

arXiv2026

BFA: Real-time Multilingual Text-to-speech Forced Alignment

We present Bournemouth Forced Aligner (BFA), a system that combines a Contextless Universal Phoneme Encoder (CUPE) with a connectionist temporal classification (CTC)based decoder. BFA introduces explicit modelling of inter-phoneme gaps and silences and hierarchical decoding strategies, enabling fine-grained boundary prediction. Evaluations on TIMIT and Buckeye corpora show that BFA achieves competitive recall relative to Montreal Forced Aligner at relaxed tolerance levels, while predicting both onset and offset boundaries for richer temporal structure. BFA processes speech up to 240x faster than MFA, enabling faster than real-time alignment. This combination of speed and silence-aware alignment opens opportunities for interactive speech applications previously constrained by slow aligners.

eess.AS↗

arXiv2026

UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models

Large language models (LLMs) have demonstrated promising performance in both automatic speech recognition (ASR) and text-to-speech (TTS) systems, gradually becoming the mainstream approach. However, most current approaches address these tasks separately rather than through a unified framework. This work aims to integrate these two tasks into one unified model. Although discrete speech tokenization enables joint modeling, its inherent information loss limits performance in both recognition and generation. In this work, we present UniVoice, a unified LLM framework through continuous representations that seamlessly integrates speech recognition and synthesis within a single model. Our approach combines the strengths of autoregressive modeling for speech recognition with flow matching for high-quality generation. To mitigate the inherent divergence between autoregressive and flow-matching models, we further design a dual attention mechanism, which switches between a causal mask for recognition and a bidirectional attention mask for synthesis. Furthermore, the proposed text-prefix-conditioned speech infilling method enables high-fidelity zero-shot voice cloning. Experimental results demonstrate that our method can achieve or exceed current single-task modeling methods in both ASR and zero-shot TTS tasks. This work explores new possibilities for end-to-end speech understanding and generation. Code is available at https://github.com/gwh22/UniVoice.

eess.AS↗

arXiv2026

X-VC: Zero-shot Streaming Voice Conversion in Codec Space

Zero-shot voice conversion (VC) aims to convert a source utterance into the voice of an unseen target speaker while preserving its linguistic content. Although recent systems have improved conversion quality, building zero-shot VC systems for interactive scenarios remains challenging because high-fidelity speaker transfer and low-latency streaming inference are difficult to achieve simultaneously. In this work, we present X-VC, a zero-shot streaming VC system that performs one-step conversion in the latent space of a pretrained neural codec. X-VC uses a dual-conditioning acoustic converter that jointly models source codec latents and frame-level acoustic conditions derived from target reference speech, while injecting utterance-level target speaker information through adaptive normalization. To reduce the mismatch between training and inference, we train the model with generated paired data and a role-assignment strategy that combines standard, reconstruction, and reversed modes. For streaming inference, we further adopt a chunkwise inference scheme with overlap smoothing that is aligned with the segment-based training paradigm of the codec. Experiments on Seed-TTS-Eval show that X-VC achieves the best streaming WER in both English and Chinese, strong speaker similarity in same-language and cross-lingual settings, and substantially lower offline real-time factor than the compared baselines. These results suggest that codec-space one-step conversion is a practical approach for building high-quality low-latency zero-shot VC systems. Our audio samples, code and checkpoints are released at https://github.com/Jerrister/X-VC.

eess.AS↗

arXiv2026

What Selects, What Reconstructs: Repairing Exemplar-Based Complex-Spectrum Separation

Exemplar methods separate a mixture by picking one learned spectrum per source and deforming it until it explains the observation, making one deformation class both reconstructor and selector. We show that the second role is empty as soon as the class can interpolate: the rule then ranks candidates on its regulariser, a choice made before the data, and the estimates sum back to the mixture whichever candidate wins. The condition is a parameter count, so the diagnosis runs before any experiment. On free per-bin deformation of complex spectra it explains the observed pathologies at once: a criterion that ranks candidates by their loudness, and half an output that is a mask on the mixture rather than an exemplar. The same theorem prescribes the repair, a selection class poorer than the reconstruction class: one complex gain and one pure delay rank the candidates, and a local combination of the best-aligned atoms, fitted jointly in closed form, rebuilds them. On MUSDB18 against the exact ceiling of the masking class, the distance between the criterion and an oracle inside its own candidate pool falls under the rigid selector from 6.2-7.7 to 0.5-2.8 dB, though only 0.9-1.2 dB of that reaches the output, and the per-frame latency of the deployed rule by a factor of 47 to 806. One lock remains, quantified: atoms are scored against the mixture, so the score carries a term for the other source that absorbs the capacity the reconstruction class gains, leaving the output 10.0 dB under the ceiling. Ranking hypotheses by the residual of a fit free enough to interpolate ranks them on the regulariser alone.

eess.SP↗

arXiv2026

Phoenix-VAD: Streaming Semantic Endpoint Detection for Full-Duplex Speech Interaction

Spoken dialogue models have significantly advanced intelligent human-computer interaction, yet they lack a plug-and-play full-duplex prediction module for semantic endpoint detection, hindering seamless audio interactions. In this paper, we introduce Phoenix-VAD, an LLM-based model that enables streaming semantic endpoint detection. Specifically, Phoenix-VAD leverages the semantic comprehension capability of the LLM and a sliding window training strategy to achieve reliable semantic endpoint detection while supporting streaming inference. Experiments on both semantically complete and incomplete speech scenarios indicate that Phoenix-VAD achieves excellent and competitive performance. Furthermore, this design enables the full-duplex prediction module to be optimized independently of the dialogue model, providing more reliable and flexible support for next-generation human-computer interaction.

eess.AS↗

arXiv2026

VoxPrivacy: A Benchmark for Evaluating Interactional Privacy of Speech Language Models

As Speech Language Models (SLMs) transition from personal devices to shared, multi-user environments such as smart homes, a new challenge emerges: the model is expected to distinguish between users to manage information flow appropriately. Without this capability, an SLM could reveal one user's confidential schedule to another, a privacy failure we term interactional privacy. Thus, the ability to generate speaker-aware responses becomes essential for SLM safe deployment. Current SLM benchmarks test dialogue ability but overlook speaker identity. Multi-speaker benchmarks check who said what without assessing whether SLMs adapt their responses. Privacy benchmarks focus on globally sensitive data (e.g., bank passwords) while neglecting contextual privacy-sensitive information (e.g., a user's private appointment). To address this gap, we introduce VoxPrivacy, the first benchmark designed to evaluate interactional privacy in SLMs. VoxPrivacy spans three tiers of increasing difficulty, from following direct secrecy commands to proactively protecting privacy. Our evaluation of nine SLMs on a 32-hour bilingual dataset reveals a widespread vulnerability: most open-source models perform close to random chance (around 50% accuracy) on conditional privacy decisions, while even strong closed-source systems fall short on proactive privacy inference. We further validate these findings on Real-VoxPrivacy, a human-recorded subset, confirming that failures observed on synthetic data persist in real speech. Finally, we demonstrate a viable path forward: by fine-tuning on a new 4,000-hour training set, we improve privacy-preserving abilities while maintaining robustness. To support future work, we release the VoxPrivacy benchmark, the large-scale training set, and the fine-tuned model to foster the development of safer and more context-aware SLMs.

eess.AS↗

arXiv2026

Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe

Probing is widely used to study which features can be decoded from language model representations. However, the common decoding probe approach has two limitations that we aim to solve with our new encoding probe approach: contributions of different features to model representations cannot be directly compared, and feature correlations can affect probing results. We present an Encoding Probe that reverses this direction and reconstructs internal representations of models using interpretable features. We evaluate this method on text and speech transformer models, using feature sets spanning acoustics, phonetics, syntax, lexicon, and speaker identity. Our results suggest that speaker-related effects vary strongly across different training objectives and datasets, while syntactic and lexical features contribute independently to reconstruction. These results show that the Encoding Probe provides a complementary perspective on interpreting model representations beyond decodability.

cs.CL↗

arXiv2026

EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement

Audio tokenizers serve as the discrete interface between continuous audio and Audio Language Models (ALMs), but existing tokenizers often struggle to support both understanding and generation. Reconstruction-oriented codecs preserve acoustic fidelity but lack rich semantics, while semantic-aware tokenizers typically rely on separate semantic and acoustic streams, introducing redundancy or misalignment. We propose \textbf{EntangleCodec}, a unified discrete audio tokenizer that learns caption-aligned semantic-acoustic representations before quantization. By aligning audio with rich captions rather than ASR transcripts, EntangleCodec captures linguistic content, speaker identity, emotion, prosody, and acoustic scenes within a compact token stream. A flow-matching diffusion decoder further enables high-quality reconstruction across speech, music, and general audio. EntangleCodec achieves reconstruction quality competitive with specialized codecs, outperforms all codec-based baselines on audio understanding by up to \textbf{+7.4\%} on MMAR, and supports both TTS and TTA generation in a unified framework. Furthermore, EntangleCodec-based audio language models demonstrate strong scaling behavior: even at \textit{0.6B} parameters, the model surpasses specialized continuous-representation LLMs with over \textit{13B} parameters across three benchmarks using \textbf{22$\times$} fewer parameters; scaling to \textit{8B} further establishes new state-of-the-art results on MMAR, highlighting that representation quality is as critical as model scale in audio language modeling. Code and model weights are available at https://github.com/luckyerr/EntangleCodec.

cs.SD↗

arXiv2026

Alignment-Free Text-Audiobox for Voice Dubbing and Full-Duplex Dialogue Synthesis

We present Alignment-Free Text-Audiobox (Text-AB), a unified framework for high-quality voice dubbing and full-duplex dialogue synthesis. Building on a Diffusion Transformer trained with a flow-matching objective, Text-AB departs from the Audiobox system along three dimensions. First, it operates in a latent diffusion framework using DAC-VAE features that encode 48 kHz waveforms into a 25 Hz latent sequence, giving over 10x higher compression than previous EnCodec representations while improving resynthesis quality. Second, Text-AB is alignment-free: it consumes raw text via an off-the-shelf text encoder and learns text-speech alignment through cross-attention, removing the need for forced alignment and explicit duration prediction. Third, we scale model and data substantially, pretraining a 3B-parameter model on 480k hours of monolingual speech, followed by supervised fine-tuning on three downstream tasks: cross-lingual voice dubbing, full-duplex dialogue synthesis, and emotional full-duplex dialogue synthesis. At inference, Text-AB supports one-shot generation for up to ~1 min of speech and arbitrarily long-form generation via a multi-diffusion scheme, plus a multi-stage reranking strategy that enhances quality based on automated metrics. On a real-world dubbing benchmark, Text-AB delivers a step-change improvement over the latest internal dubbing system, with large gains in prosody similarity, voice similarity, naturalness, and shareability. For full-duplex dialogue synthesis, it approaches human recordings on short-form conversations and substantially outperforms the latest internal model on long-form human-likeness and expressivity, while natively modeling turn-taking, back-channeling, and emotional dynamics. For emotional dialogue synthesis, emotion conditioning significantly improves emotion alignment and emotional interaction quality over the unconditioned baseline.

cs.CL↗

arXiv2026

Scalable Context Orchestration for Serving LLMs Over Voice

Voice AI applications are gaining popularity as advances in large language models (LLMs) enable more natural and accessible spoken interactions. Serving these applications requires accounting not only for what users say, but also for how they speak (e.g., speaking rate) and the conditions under which their audio is captured and transmitted (e.g., background noise and packet loss). However, existing LLM systems represent conversation context as a flat, growing sequence of messages, leaving voice-specific context implicit in the audio. As a result, they can generate responses that are poorly aligned with user preferences, degrade interaction quality under adverse environmental conditions, and incur high costs over long voice sessions. We present llmovoice, a context-management middleware that explicitly models voice context and orchestrates its use. At each turn, llmovoice constructs a bounded voice context from the current user input, relevant interaction history, and explicit paralinguistic and environmental states. It then uses the serving LLM to reason over this context and generate runtime directives that guide how the system responds. We evaluate llmovoice on real-world voice applications and benchmarks. It reduces speaking-rate alignment error by 52.4%, lowers the false-interruption rate from 46.0% to 0.9% under packet loss, and reduces model usage cost by 79.2%. For long sessions, llmovoice reduces per-turn cost by up to 24.9 times while retaining up to 98.7% of baseline answer quality.

cs.SD↗

arXiv2026

Brain2Speech-Net: Intelligible, Real-Time Brain-to-Speech Synthesis Without Text Decoding

The loss of speech limits communication for individuals with paralysis. Restoring speech by synthesizing it directly from neural activity is challenging: intracortical data are scarce and lack aligned targets, so most systems rely on cascaded neural-to-text-to-speech pipelines that add latency and propagate errors. We present Brain2Speech-Net, among the first single-stage frameworks to remain intelligible under limited data while removing intermediate text decoding. A differentiable phoneme bottleneck preserves linguistic structure without explicit text decoding. A lightweight deep-HMM aligner then maps this bottleneck to contextual phoneme representations in a TTS latent space. It learns monotonic alignment between neural recordings and phoneme segments without frame-level supervision, inheriting strong acoustic priors for data-efficient training. On an intracortical dataset, Brain2Speech-Net achieves strong intelligibility in objective and listening tests while running faster than real time. Unlike cascaded systems that incur high latency and direct speech-unit models that lack intelligibility, it delivers both intelligible and real-time speech.

eess.AS↗

arXiv2026

Discriminative Flow Matching: Beyond Time-Conditioning in Generative Restoration via Flow-State Representations

Existing Conditional Flow Matching (CFM) formulations describe transport progress using an explicit interpolation coordinate, commonly interpreted as time, assuming that a single global variable adequately represents a sample's position along the generative trajectory. In restoration tasks, however, transport progress is sample-dependent because the initial distribution may exhibit varying statistical dependencies with the target distribution. Thus, samples at the same interpolation coordinate can differ substantially in degradation level, distance to the target distribution, and restoration difficulty. We investigate whether signal representations learned by discriminatively trained models provide a meaningful description of generative transport state in CFM-based restoration. Through systematic latent-space analysis, we show that discriminative representations organize according to degradation severity and follow a consistent trajectory toward the clean-data manifold during generation. Motivated by these observations, we introduce the Discriminative Flow-State Hypothesis, which posits that discriminative representations encode a transport state governing generative restoration. Based on this hypothesis, we propose Discriminative Flow Matching, which conditions the Flow-Matching velocity field on Discriminative Flow-State Representations rather than explicit time coordinates. Experiments on speech enhancement and image denoising show that these representations characterize restoration progress, enable adaptive inference, and consistently outperform CFM and diffusion-related baselines. Our findings suggest that discriminative representations provide an effective state-aware alternative to explicit time conditioning and offer a novel perspective on the relationship between discriminative and CFM-based generative modeling.

eess.AS↗

arXiv2026

Binaural Sound Event Localization and Detection based on HRTF Cues for Humanoid Robots

This paper introduces Binaural Sound Event Localization and Detection (BiSELD), a task that aims to jointly detect and localize multiple sound events using binaural audio, inspired by the spatial hearing mechanism of humans. To support this task, we present a synthetic benchmark dataset, called the Binaural Set, which simulates realistic auditory scenes using measured head-related transfer functions (HRTFs) and diverse sound events. To effectively address the BiSELD task, we propose a new input feature representation called the Binaural Time-Frequency Feature (BTFF), which encodes interaural time difference (ITD), interaural level difference (ILD), and high-frequency spectral cues (SC) from binaural signals. BTFF is composed of eight channels, including left and right mel-spectrograms, velocity-maps, SC-maps, and ITD-/ILD-maps, designed to cover different spatial cues across frequency bands and spatial axes. A CRNN-based model, BiSELDnet, is then developed to learn both spectro-temporal patterns and HRTF-based localization cues from BTFF. Experiments on the Binaural Set show that each BTFF sub-feature enhances task performance: V-map improves detection, ITD-/ILD-maps enable accurate horizontal localization, and SC-map captures vertical spatial cues. The final system achieves a SELD error of 0.110 with 87.1% F-score and 4.4° localization error, demonstrating the effectiveness of the proposed framework in mimicking human-like auditory perception.

eess.AS↗

arXiv2026

SonicCaps: Large-Scale Diverse and Fine-Grained Captioning for Improved Audio-Retrieval

Recent advances in audio-language modeling have been driven by large-scale audio captioning datasets. However, existing datasets remain limited by low semantic diversity, generic descriptions lacking acoustic details, and one-to-one audio-caption mappings that poorly reflect the inherent ambiguity of auditory perception. We introduce SonicCaps, a large-scale audio captioning dataset comprising ~15M captions paired with ~700k audio clips, generated using a multi-modal large language model (Qwen3-Omni) conditioned on both audio and text. To explicitly promote diversity, we generate around 24 captions per audio via structured prompt engineering and few- shot generation, spanning main descriptions, rephrased variants (verbosity, style) and semantic tags. Human evaluation shows that SonicCaps is rated significantly higher than existing captioning datasets, with fine-grained analyses indicating that our captions are perceived as more descriptive and precise, which strongly correlates with quality judgments. Finally, training CLAP models on SonicCaps with a multi-caption sampling strategy consistently improves audio retrieval and zero-shot classification, with stronger generalization across public and commercial benchmarks. We release both SonicCaps and two specialized CLAP models on hugging face: https://huggingface.co/datasets/Zineb/SonicCaps.

cs.SD↗

arXiv2026

GhostWord: A Fine-Grained Backdoor Attack on Automatic Speech Recognition

Automatic Speech Recognition (ASR) systems are widely deployed in safety-critical settings but remain vulnerable to data-poisoning backdoor attacks. Existing ASR backdoors typically use phrase-level triggers paired with a fixed target sentence, creating strong artifacts (e.g., repeated transcripts or triggers placed in non-speech regions) that simple preprocessing can mitigate. We propose GhostWord, a word-level, time-localized ASR backdoor that uses codebooks mapping short ($\approx$400\,ms) acoustic triggers to target words. During poisoning, we inject a trigger into the forced-aligned time span of a chosen source word in the audio and replace only that word in the transcript, enabling precise semantic flips and composable sentence manipulation while avoiding many-to-one label artifacts. Across Common Voice (v23 English, v24 Lithuanian) and multiple backbones (Whisper-Small/Medium, MMS, SpeechT5), GhostWord achieves an average attack success rate of 89.3\% and transfers across languages and models. Adapting optimization-based defenses (ABL, ANP, SAU, I-BAU) reveals a sharp robustness--accuracy trade-off: attack success drops from 89.3\% to 29.1\% while clean WER rises from 21.5\% to 45.0\%, consistent with our theoretical analysis showing that, in high-vocabulary models, backdoor suppression structurally tends to degrade clean performance. The source code is publicly available at https://github.com/rohban-lab/GhostWord

eess.AS↗