A capable voice assistant must do more than recognize words; it must understand requests, reason over context, sustain conversations, and act through tools. We present Apriel Voice 27B Preview, an open speech-language model that unifies these capabilities within a shared reasoning backbone while retaining text and image input modalities. Built on the post-trained Gemma 4 26B-A4B checkpoint, Apriel Voice directly processes speech and generates both responses and tool calls without requiring a separate dialogue model. We introduce a two-stage training procedure to adapt the model to speech. The first stage establishes the speech interface, while the second jointly adapts the projector and backbone through supervised fine-tuning, text replay, and source-dependent cross-entropy and forward Kullback--Leibler divergence supervision. Automatically constructed speech-conditioned dialogues provide conversational training data, while local teacher serving, overlapping teacher and student computation, and fused full-vocabulary losses enable efficient online distillation. In thinking mode, Apriel Voice achieves a score of 98.90 on Big Bench Audio, 81.13 on Speech-BFCL, and a task success rate of 65.51% on $\tau$-Voice, with a mean latency of 1.91 seconds. It also achieves 51.27% English EVA accuracy and 74.13% experience pass@1. Finally, we deploy Apriel Voice 27B Preview on a custom serving platform to support interactive voice interactions.
https://arxiv.org/abs/2610.40738
Audio descriptions (AD) are essential for making visual media accessible to blind and low-vision (BLV) users. While Multimodal Large Language Models (MLLMs) offer a scalable solution for generating audio descriptions on-demand, their performance on ``inline'' audio descriptions -- which must fit within existing silences in a video -- remains under-explored, particularly for diverse user-generated content (UGC). We present a comprehensive investigation into MLLM-generated inline audio descriptions. First, we introduce MTG-AD, a professionally annotated dataset of 36 hours of videos, each averaging $\sim$5 mins. and 8k+ descriptions in total, co-created by paired blind and sighted AD professionals to provide a high-quality benchmark for this task. Second, we propose MTG-AD-Eval, an evaluation framework based on audio description expert guidelines that provides fine-grained, reference-free actionable metrics for model improvement. Crucially, our framework evaluates the end-to-end task: it renders the generated scripts into audio tracks to assess their fit within the original video's natural silences, minimizing disruptive overlaps. Our analysis across frontier MLLMs reveals that while models accurately describe visual events and substantially reduce speech overlaps, gaps persist in narrative pacing and flow. Finally, we empirically validate that our automated and reference-free metrics correlate significantly with human quality ratings from sighted raters and 7 BLV participants, finding that while users narrowly prefer human-authored audio descriptions, they find MLLM-generated audio descriptions highly beneficial for comprehension. We provide actionable system design guidance and release MTG-AD at this https URL and MTG-AD-Eval at this https URL.
https://arxiv.org/abs/2610.39955
End-of-turn (EoT) detection has been studied mostly through features, models, and modalities, while the speech genre of the training data has drawn far less attention. We isolate this factor. Using one reproducible annotation pipeline, we build a matched pair of corpora, multi-turn human-human conversational and single-turn human-machine, and train the same streaming ConvLSTM EoT detector on each. Across four test sets the conversational model reaches up to +0.45 higher F1, driven by fewer false alarms on the mid-turn pauses and hesitations that are rare in single-turn corpora. This conversational-training effect is not specific to frame-level decoding. Under a matched complete-or-not test it also appears at the utterance level, across two encoders, but only on conversational test data. Testing only on single-turn speech, as most prior work does, therefore hides the benefit of conversational training data. Against open-source baselines, our 1.8M-parameter model attains the highest F1 on every test set.
https://arxiv.org/abs/2610.39742
Quantifying degradation between a pristine signal and its degraded observation is fundamental to signal processing, yet existing full-reference measures are inherently modality-specific. We introduce SymKL, a unified full-reference degradation measure based on implicit neural representations (INRs). An INR is fitted once to the pristine reference and characterized by its diagonal Fisher information, which captures the local information geometry of the learned representation. Evaluating the Fisher information with the pristine reference and a degraded observation yields two parameter-sensitivity profiles whose symmetric KL divergence defines the degradation score. The proposed formulation requires only the reference and degraded observation, without knowledge of the corruption process or degradation severity, making it applicable across images, audio, and 3D data. We further derive an exact closed-form expression for the diagonal Fisher of SIREN, enabling efficient computation. Experiments on image, speech, and volumetric 3D benchmarks demonstrate that SymKL accurately tracks degradation severity, remains monotonic where conventional metrics saturate or fail, and provides a unified modality-agnostic measure of signal degradation. Code will be made publicly available after the review process.
https://arxiv.org/abs/2610.39403
We present our submission to the Beyond Transcription Challenge (BeTraC) on medical note generation from doctor-patient audio conversations. We propose a section-aware approach based on Qwen2.5-Omni-3B, in which a lightweight Q-Former learns SOAP section-specific queries to extract compact clinical representations from speech. In the lightweight track, our system ranks fourth and substantially outperforms the challenge baseline, achieving a Concept F1 of 0.5005 on the official test set. The organizers' analysis and our heuristic evaluation suggest improved robustness to hallucinations, and better stability under difficult audio conditions. These results show that explicitly modeling SOAP structure through section-specific queries is an effective way to improve the faithfulness and reliability of audio-based medical note generation.
https://arxiv.org/abs/2610.40695
Large audio language models (LALMs) can process speech directly, but it remains unclear how well they use the non-lexical acoustic information that speech carries. We study this question through pain, using TAME-Pain, which contains pain-neutral Harvard sentences and spoken pain ratings recorded at different self-reported pain levels. We introduce HEAR, a four-stage diagnostic framework that traces pain-related information from the speech signal to the model's prediction, and apply it to seven closed-source and open-weight LALMs. On the Harvard sentences, where pain can only be inferred from the voice, all models perform at chance level, and same-speaker references or few-shot examples improve balanced accuracy by no more than six points. On the spoken ratings, the same models reach 87.5-99.7% balanced accuracy. Layer-wise probing of open-weight LALMs shows that pain can be decoded from early audio representations (74.1% balanced accuracy for binary prediction and 45.0% for three-class severity), but that this information, along with most pain-associated acoustic cues, decreases in deeper layers. In an acoustic perception test, weaker models cannot distinguish even large changes in these cues, whereas stronger models can but still fail to infer pain. Finally, we recover pain-related acoustic cues and directly reinject them as structured text into the prompt, which improves pairwise pain prediction by up to 32 points. These results indicate that current LALMs encode paralinguistic information in early layers that is largely unavailable when the model produces its answer.
https://arxiv.org/abs/2610.38570
Music audio generation spans instrumental clips, full songs with vocals, edits of existing recordings, and systems that play alongside a musician in real time. This monograph explains the methods behind these systems for readers familiar with neural-network training who are new to music generation. It introduces neural audio codecs and autoencoders, autoregressive and masked token models, diffusion and flow matching, sampling acceleration, and preference optimization in a shared notation. Worked examples connect training objectives and sampling procedures to published systems. The application sections relate the musical requirements of instrumental generation, songs, editing, and live performance to model design. Comparison tables record representations, methods, inputs, tasks, and release information documented in papers and official sources. Symbolic composition, speech, and sound effects are included where they connect to music audio. We explain how to interpret automatic metrics and learned judges, design and report listening tests, and assess evidence about data provenance, memorization, attribution, and output detection. Selected legal decisions and disputes illustrate the implications for training and release. The reviewed systems combine established generative paradigms with new representations, planning stages, and post-training procedures. Differences in data, scale, and evaluation limit what cross-system comparisons can establish about the sources of reported gains.
https://arxiv.org/abs/2610.38252
Automatic speech recognition (ASR) systems often perform less accurately for speakers of regional dialects, but less is known about how users respond to these limitations and how regional voices produced by voice assistants (VAs) are evaluated through a sociolinguistic lens. This study investigates these issues among speakers of Newcastle English (Geordies), examining both linguistic accommodation to voice technologies and perceptions of regional versus mainstream-accented VA voices. Participants interacted with a simulated VA that spoke either Newcastle English or Standard Southern British English (SSBE). They subsequently completed semi-structured interviews about their experiences with the experimental VA and voice technologies, language use, accent attitudes, and place orientation. The findings reveal a two-way process of sociolinguistic bias. The Geordie VA was associated with familiarity, warmth, personality, and local belonging, but also with concerns about professionalism and authority, whereas the SSBE voice was perceived as more neutral, clear, and credible. Participants also reported adapting their speech when voice technologies failed to recognise them, most commonly by shifting to a more mainstream accent, enunciating more clearly, and speaking more slowly. These strategies are similar to accommodation in human-human interaction and reflect users' perceptions of what technologies can recognise, also known as perceived intelligibility pressures. Overall, the findings demonstrate that voice technologies can reproduce existing accent biases both by encouraging users to suppress regional features and by activating established social stereotypes through synthetic voices. The study positions sociolinguistics as a bridge between understanding human-AI interaction and designing inclusive technologies around users' own linguistic priorities.
https://arxiv.org/abs/2610.38005
Time-series data play an important role in various tasks, such as weather forecasting, web traffic analysis, and speech recognition. Recently, pioneering studies have increasingly adopted Joint-Embedding Predictive Architecture (JEPA) based encoders to learn time-series representations through latent-space prediction. However, they often overlook the underlying factors governing transitions between time-series observations. In this work, we hypothesize that explicitly modeling the information behind changes in time series can facilitate time-series modeling. Building on this hypothesis, we propose ACTS-WM, a self-supervised latent action-conditioned world model framework for time-series analysis. First, we introduce a latent action modeling approach that infers the underlying information behind time-series transitions as latent actions, without requiring explicit action annotations. We then develop a JEPA-based encoder and an action-conditioned world model to predict target time-series representations conditioned on the learned latent actions and task information. We evaluate ACTS-WM across 4 representative tasks on 22 datasets from diverse domains, covering univariate and multivariate forecasting and classification. Comprehensive experiments demonstrate that ACTS-WM can improve downstream performance over pretrained JEPA-based encoders by learning complementary representations.
https://arxiv.org/abs/2610.37963
The hybrid work trend in the post-COVID period has transformed how people communicate while at work. However, there is a lack of quantitative understanding of how home and office environments shape communicative behavior and affective well-being. To study this, as a part of a larger study of the role of work environment on stress, we designed an egocentric wearable audio sensing system that captured interpersonal communication across both working locations. The system extracts real-time acoustic features on a wearable audio sensor and performs offline foreground speaker diarization to derive speaking load and activeness features. To improve diarization performance under low-dimensional feature constraints, we apply a teacher-student knowledge distillation framework that transfers knowledge from large-scale speech foundation models into a compact ResNet-based model, achieving consistent improvements in diarization performance over the baseline across three public egocentric speech datasets. In a four-month longitudinal deployment with 16 participants, our system revealed location-dependent differences in work communication patterns. Moreover, the mixed linear model analyses showed that office-based speaking load was significantly associated with higher self-reported stress and lower self-reported productivity, while speaking activeness during home-based work amplified both productivity and affective load in this cohort.
https://arxiv.org/abs/2610.37270
Synthetic text generation offers a promising approach to alleviating data scarcity in low-resource languages. However, its effectiveness is inherently limited for languages that are scarcely represented, or entirely absent, in an LLM's pretraining data. At the same time, many such languages have human-curated vocabularies that provide rich lexical and semantic information, often accompanied by grammatical information such as part-of-speech labels. In this work, we ask whether LLMs can leverage these resources to generate coherent text in extremely low-resource and unseen languages. We introduce a framework that combines human-curated vocabularies with a small number of human-written exemplars that provide syntactic signals, while sampling candidate words according to a Zipfian distribution. Across languages with varying levels of resource availability, we evaluate the generated text using lexical diversity, off-target ratio, and human judgments of fluency. Our results show that reasoning-enabled LLMs can generate fluent text even in extremely low-resource languages, with particularly strong results at the sentence level and promising performance at the paragraph level. Our findings highlight a practical pathway for bootstrapping synthetic data in low-resource languages, expanding the amount of usable text even when existing digital resources are extremely limited. Our source code is available at this https URL.
https://arxiv.org/abs/2610.37105
Although the recent development of LLMs has paved the way for multi-modal interaction, minority languages face difficulties keeping pace. This work presents the first open Speech Language Model for Basque, designed for low-latency, end-to-end spoken interaction. Based on the LLaMA-Omni architecture, the system integrates a Latxa model as its backbone, transferring its Basque capabilities to the spoken modality by fine-tuning several modules. To address data scarcity, the English VoiceAssistant-400K corpus was translated into Basque, and the audio was synthesized using a Basque TTS. Evaluation results confirm the system's viability, achieving 3.86/5 in content quality, a 9.94% WER for spoken intelligibility, and a 3.07 UTMOS for audio quality. This work demonstrates that advanced spoken interaction systems can be developed using modular architectures and synthetic data even in low-resource languages.
https://arxiv.org/abs/2610.36911
Speech enhancement (SE) systems are commonly evaluated with objective metrics, with and without references, and with categorical subjective listening tests, all measuring speech quality and intelligibility. So far, it is unclear from such evaluations whether the processed speech is perceptually different or is preferred by everyday listeners. We investigate discrimination and preference as complementary dimensions of SE evaluation through crowdsourced triangle and pairwise preference tests across four SE systems, with comparisons to clean references. Results show that both listeners' ability to distinguish and whether they exhibit systematic preference vary across systems and substantially across acoustic conditions. Pairwise evaluations of objective metrics showed variable correlation with both discriminability and preference, motivating further studies into these novel aspects in speech enhancement evaluation.
https://arxiv.org/abs/2610.36892
Streaming speech-to-speech translation requires timely decisions about when partial input is sufficient for accurate translation. We present S3-S2ST, a model that learns to translate and speak from semantically aligned streaming supervision. By converting utterance-level speech pairs into incremental training examples, we teach a learned policy when to commit translations. Its adjustable threshold controls the quality--latency tradeoff on a fixed 640\,ms input grid. S3-S2ST delivers competitive English--Chinese translation on FLEURS and leads the evaluated streaming systems in translation quality on the internal 9-pair test set. On RealSI, adapting the threshold to buffered speech further improves quality over a low fixed threshold with little change in first-audio latency. We plan to release the model and code.
https://arxiv.org/abs/2610.36777
Voice anonymization aims to protect a speaker's identity while preserving the linguistic content of speech, enabling voice data to be shared and processed with reduced privacy risk. This work focuses on reversible voice anonymization, where the original voice can be recovered by an authorized user rather than being permanently discarded. However, existing approaches can achieve apparent speaker anonymization by degrading the speech itself, while their effectiveness may also depend on the speaker-verification representation used during training. This creates a need for methods that protect speaker identity without sacrificing speech intelligibility and that remain effective against unseen speaker verifiers. We introduce content preserving training constraints to improve the privacy-utility trade-off by preventing anonymization from being achieved primarily through speech degradation. We further introduce a verifier-generalization strategy that incorporates a stronger speaker-verification representation during training, improving anonymization robustness beyond the verifier used in the original training setup. The resulting approach maintains intelligible speech, strengthens anonymization, and preserves reliable voice restoration, with evaluation on unseen speakers and held-out speaker verification models. On 38 unseen speakers, the approach raises the attacker's equal error rate from a measured floor of 2.8% to 26.3%, and to 27.9% against a held-out verifier, with 11.8% word error rate and 94.9% speaker similarity on key-based restoration. These improvements advance reversible voice anonymization toward practical privacy-preserving speech applications, where anonymized speech can be safely processed or shared while the original voice remains recoverable under authorized conditions.
https://arxiv.org/abs/2610.36768
Modern language models are trained on far more language than children experience, but we know much less about learning from small, naturalistic datasets. We train small GPT-2 models on transcripts of speech with children from dense home recordings (BabyView) and on synthetic child-directed dialogue (TinyDialogues), varying the amount, source, and diversity of training data. Models trained on one child's language environment predict that environment substantially better than other children's environments. Much of this specialization is lexical and distributional: a simple 5-gram model reproduces the cross-child pattern (r=.91). Training on data from multiple children clearly improves prediction of pooled held-out language relative to training on a single child's input without a similarly clear improvement on grammatical benchmarks. Across data sizes, naturalistic and synthetic training inputs also produce different grammatical and lexical-semantic patterns, with important differences between grammatical phenomena. Together, these results show that small-data language learning depends not only on how much language a model sees, but on which environments it comes from and how well that input matches what the model is asked to predict.
https://arxiv.org/abs/2610.36679
Streaming audio-visual target speaker extraction (AV-TSE) uses a target speaker's face to extract the speaker's speech from an input audio mixture in real time. However, existing systems fix the target speaker for an entire clip, while conversation demands frequent and immediate target switches. To address this problem, we propose Tap2Listen, a streaming AV-TSE model designed for instant response to target switches. The model separates computation by modality: the target-agnostic audio encoder processes only the mixture, while the target-specific visual cues of the selected face condition only the decoder. A switch requires only a 0.12ms re-projection and takes effect immediately. We also design component-wise losses: a prediction loss for the encoder and a supervised extraction loss for the decoder. For evaluation, we measure how quickly output quality recovers after a switch. On the standard LRS3-2mix test set, Tap2Listen improves SI-SNRi from 8.85 to 9.68 dB at a comparable parameter count. After a switch to a known face, the model produces full-quality output from the first frame, whereas the baseline needs about 1 second to recover. Finally, we show that the proposed streaming AV-TSE model runs in real time on a single CPU core.
https://arxiv.org/abs/2610.36643
Real-world audio applications require precise, queryable representations grounded in physical time. Yet modern Large Audio-Language Models (LALMs) increasingly favor conversational generation, producing free-form descriptions that conflate acoustic perception with higher-level reasoning and lack precise temporal grounding. We introduce TAC2, a foundation model that casts timestamped audio captioning as composable functions to construct granular, speaker-attributed acoustic timelines directly from in-the-wild audio. To avoid prohibitively expensive manual annotation, we programmatically fuse complementary predictions from specialized weak teachers through time-registered IoU matching. We model the resulting multi-granularity schema of timestamped events, speaker turns, and fine-grained speech attributes using an Instruction-Input-Output (IIO) completion format, in which each task is a function of the audio, an instruction, and an optional input. A single call decodes the full description autonomously, while composing calls lets earlier outputs or external priors, such as a reference transcript, condition later ones. We further extend TAC2 with expressive speech attributes to obtain TAC2-S, using parameter-efficient specialists to elicit latent paralinguistic capabilities from the pre-trained backbone and distill them into a unified model. We validate the resulting representation in two complementary settings. Paired with frozen text-only LLMs, it yields strong spoken audio understanding across diverse reasoning backends, demonstrating the utility of decoupling fine-grained acoustic perception from downstream reasoning. Used as paired supervision for text-to-audio generation, it supports semantically and temporally grounded reconstruction, together with explicit zero-shot control over event timing, speaker attributes, and word-level emphasis.
https://arxiv.org/abs/2610.36568
Multilingual automatic speech recognition (ASR) has achieved rapid progress with large-scale pretrained models and multilingual speech corpora. Previous studies have proved the pivotal role of data sampling in multilingual ASR performance. However, existing sampling strategies largely rely on time-consuming manual, heuristic-based designs. To address this, we propose a linguistic-aware agentic data sampling framework that introduces a data sampling LLM agent into the multilingual ASR training loop. The agent is driven by a linguistically grounded rubric that analyzes ASR errors from phonological, morphological, and syntactic perspectives, and uses the resulting feedback together with training statistics, budget constraints, and algorithm profiles to select domain-level, sample-level, and token-level sampling strategies. This design turns evaluation results into adaptive data-selection decisions rather than treating WER/CER as final endpoints only. We conduct experiments on twelve Common Voice languages using Whisper-medium as the ASR backbone. The results show that our method achieves performance better than full-data training while using less training data and lower computational resources, and substantially accelerates training convergence compared to conventional sampling strategies.
https://arxiv.org/abs/2610.36538
Written transcripts of the same speech can differ in ways that are not uniquely determined by the speech signal. We formulate evaluation-side transcript canonicalization (ETC), which maps multiple surface forms to a single canonical form when their differences are not determined by speech. To our knowledge, ETC-Bench is the first and most comprehensive multilingual benchmark for evaluation-side transcript canonicalization, covering 181 phenomenon types across 12 languages. Each instance is a minimal pair that shares a sentence context and differs only in a target span exhibiting one phenomenon. To evaluate both canonicalization success and semantic preservation, we propose Semantic-preserving Exact-match Normalization Accuracy (SENA), which combines exact agreement between independently canonicalized pair members with a pair-relative BERTScore constraint against information loss. We further introduce the Taxonomy-guided Agent Canonicalization Skill (TACS), which provides LLM agents with phenomenon descriptions and explicit canonicalization contracts. Experiments with five baseline configurations and three TACS-based agents show that the agents outperform the baseline systems on shared languages. ETC-Bench provides a systematic testbed for evaluation-side transcript canonicalization across languages.
https://arxiv.org/abs/2610.36527