arXiv subjects

Tiantian Feng

Publications and source records attributed to Tiantian Feng.

At least 19 recordsLinked to original sources

arXiv2026

Understanding Everyday Communication Patterns, Stress, and Productivity in Hybrid Work through Egocentric Wearable Audio Sensing

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.

cs.SD↗

arXiv2026

ASR-Protected Fusion and Reference-Anchored Policy Optimization for Joint ASR and Word-Level Speech Anti-Spoofing

Existing anti-spoofing systems report either an utterance-level score or a time-based spoof interval: the former cannot show which words are spoofed, while the latter does not directly match the transcript and must be post-aligned with words, so alignment errors can lead to wrong word-level labels. Standard ASR model outputs only text; spoof information in the audio is lost after recognition and is not passed with the transcript. Yet changing only a few words can change the meaning of a sentence, leaving downstream systems to use incorrect text without knowing which words are spoofed. We therefore treat partial anti-spoofing as tagged ASR: the model transcribes speech and marks spoofed words at the same time, directly linking spoof labels to output words. We adopt the audio LLM and use ASR-Protected Subspace Gated Fusion (APSGF) to fuse spoof cues with ASR features. Spoof cues are added only outside an ASR-protected subspace, so they do not disturb recognition features. After cross-entropy training, we fine-tune the model with Reference-Anchored Policy Optimization (RAPO). Since the SFT policy is already concentrated, multiple samples from the same input tend to receive similar rewards, resulting in weak group-wise advantages. RAPO instead generates a single sample with low sampling randomness and anchors its advantage to the reward of a reference model. This allows the model to reinforce responses that outperform the reference while suppressing those that underperform it. Experiments on five datasets demonstrate the effectiveness of our approach in jointly detecting spoofed words and preserving ASR accuracy. The code is publicly available.

cs.SD↗

arXiv2026

Uni-Stream: A Unified Streaming Speech Language Model for Speech Synthesis and Recognition

Unified streaming speech language models aim to support speech recognition and synthesis within a single model, enabling real-time human-computer interaction. However, jointly supporting these two directions of speech-text conversion while preserving task-specific performance remains challenging. We propose Uni-Stream, a unified streaming speech language model built on compact pretrained speech models. Uni-Stream processes interleaved text and speech in a streaming format and achieves performance comparable to task-specific models through two-stage training. We also develop a data annotation pipeline for streaming training and will publicly release the generated transcriptions and word-level timestamps. We further examine Uni-Stream's representations across tasks and modalities and find that speech and text residence in distinct latent feature space even when trained in a unified model architecture, while representations within each modality become more task-dependent in later layers.

eess.AS↗

arXiv2026

SPARC: Spoken Profile Authorship Recognition Corpus

Speech anonymization has focused on the acoustic signal, leaving open how much speaker information the transcribed words themselves retain. In this work, we study pairwise speaker and demographic-attribute verification from transcribed speech. We introduce SPARC (Spoken Profile Authorship Recognition Corpus), a benchmark built from two podcast corpora comprising over 12,500 speakers, 1.5M quality-filtered utterances, and speaker-level inferred or source-provided labels for sex, age, and accent, and evaluate five attribution models and three LLMs on identity- and attribute-verification trials with episode- and metadata-based topic proxies. LLM adversaries distinguish same-speaker pairs from text alone. Attribute-label agreement is harder to verify, but LLMs perform sex- and accent-label verification above chance. Finally, releasing only short probe texts (50 words) degrades the strongest adversaries the most, offering a partial reduction in observed linkage.

cs.CL↗

arXiv2026

PEDBench: Can Speech Models Detect Phonetic Errors?

Phonetic error detection (PED) aims to identify phoneme-level substitutions, deletions, and insertions and is essential for educational and clinical speech assessment and intervention. Despite recent advances in speech models for phoneme recognition, their ability to reliably detect fine-grained phonetic errors remains unclear because of a lack of high-quality evaluation data. To address this gap, we introduce PEDBench, the first PED benchmark spanning a continuum from natural to controlled speech. It comprises real-world recordings of spoken errors made by children (N=334), scripted error productions by human actors (N=1,188), and synthetic error productions generated using phone-conditioned text-to-speech (N=1,083). All phonetic annotations were transcribed and verified by two phonetically trained annotators. Our evaluation of 13 state-of-the-art speech models shows that they fail to reliably detect phonetic errors, even under controlled conditions with acted and synthetic speech, where acoustic variability is reduced. The models also exhibit low precision, frequently misclassifying correctly pronounced phonemes as errors. Our speech-language models, fine-tuned on synthetic data, outperform commercial and open-source baselines on word-level PED, although a sim-to-real domain gap remains. We plan to publicly release our code and recipes, along with our acted and synthetic datasets, to support the development of more accurate PED systems.

cs.CL↗

arXiv2026

Probing Neural Audio Codecs with Speaker Traits and Speech Characteristics

Neural audio codecs are increasingly used for low-bitrate speech coding and serve as tokenizers for speech language models, yet it remains unclear how their codebook hierarchies encode speaker traits and speech characteristics. We systematically study 17 multi-codebook neural audio codecs across seven traits: sex, age, accent, voice quality, emotion, speech flow, and non-verbal sounds. For each codec, we reconstruct speech using partial codebooks and use machine listeners to compare trait predictions on each reconstruction. We measure prediction agreement with reweighted Cohen's \k{appa}, and define trait depth as a proxy for the codebook depth by which each trait is encoded and recoverable. Overall, sex has the shallowest trait depth, followed by speech flow, whereas voice quality and age group require deeper stacks; emotion, accent, and non-verbal sounds fall in between. Within each trait, speech-flow classes are at relatively similar trait depths, whereas emotion, accent, and non-verbal sounds differ more. Additionally, we explore how certain codec design choices relate to trait depths. These findings show that codebook hierarchies are trait-dependent and may not exhibit uniform coarse-to-fine structures, motivating trait-specific codec evaluation and design for future applications.

eess.AS↗

arXiv2026

Towards Automated Clinical Behavioral Coding with Large Language Models: A Case study Using BOSCC recordings of Children

Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by differences in social communication and by restricted interests and repetitive behaviors. Treatment interventions often target social-communication skills, creating a need for reliable measures of behavioral change. The Brief Observation of Social Communication Change (BOSCC) is a validated treatment-response measure based on brief play and social-communication interactions between a child and trained examiner. The BOSCC coding process is resource-intensive and requires trained experts, motivating the automation of coding in order to improve scalability and accessibility. In this work, we evaluate general-purpose large language models (LLMs) for predicting speech-related BOSCC codes from different input representations. We compare transcript, diarized-transcript, and targeted audio conditions across 163 in-house recordings. LLMs are able to perform well in assessing verbal exchange, but do not perform as well when identifying atypical speech patterns. Additionally, performance varies considerably across scoring decisions, with no consistent pattern across diagnosis groups. An audit of model predictions indicates that applying the BOSCC coding criteria and interpreting ambiguous speech evidence remain challenges.

eess.AS↗

arXiv2026

Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker Traits and Speech Properties

We introduce Vox-Profile, a comprehensive benchmark to characterize rich speaker traits and speech properties using speech foundation models. Unlike prior work that targets a single dimension of speaker traits, Vox-Profile provides holistic and multi-dimensional profiles spanning both static speaker traits (e.g., age, sex, accent, voice quality) and dynamic speech traits (e.g., emotion, speech flow). This benchmark is grounded in speech science and linguistics, developed with domain experts to accurately index speaker and speech characteristics. We report benchmark experiments using over 15 publicly available speech datasets and several widely used speech foundation models that target various static and dynamic speaker and speech properties. In addition to benchmark experiments, we showcase several downstream applications supported by Vox-Profile. First, we show that Vox-Profile can augment existing speech recognition datasets to analyze ASR performance variability. Vox-Profile is also used as a tool to evaluate the performance of speech generation systems. Finally, we assess the quality of our automated profiles through comparison with human evaluation and show convergent validity. Vox-Profile is publicly available at: https://github.com/tiantiaf0627/vox-profile-release.

cs.SD↗

arXiv2026

ChildVox: A Speech, Audio, and Large Audio-Language Model Benchmark in Understanding and Characterizing Sound across Childhood

We present ChildVox, a novel benchmark for characterizing the diverse acoustic signals through which children communicate. Specifically, ChildVox follows the full developmental trajectory from birth through school age, covering physiological sounds, non-linguistic vocalizations, canonical syllables, and spoken language. ChildVox integrates more than 20 sub-tasks across 17 child-centered audio and speech datasets, enabling systematic cross-corpus and cross-domain comparison. We evaluate a representative range of audio and speech foundation models, including self-supervised, ASR-oriented, and large audio-language models, on tasks including physiological sound classification, vocalization and canonical syllables modeling, and speech quality assessment and recognition. Benchmark results show that ChildVox provides a suite of high-performance models in recognizing a wide range of acoustic signals from children, supporting downstream applications such as characterizing children's language levels and tracking speech production with age. Our benchmark models on public datasets are released at: https://github.com/tiantiaf0627/childvox-release.

cs.SD↗

arXiv2026

MyoCodec: A Streaming Neural Codec for Electromyography

Neural codecs encode continuous signals into compact sequences of discrete tokens, providing an interface for efficient transmission, storage, and token-based sequence modeling. This paradigm has been widely adopted in modern speech and audio frameworks; however, the biosignal domain still lacks a neural codec designed specifically for low-bitrate streaming and generalization across diverse downstream tasks. We present MyoCodec, a streaming neural codec designed for electromyography (EMG). Inspired by recent neural audio codecs, MyoCodec combines causal Transformers with residual vector quantization to encode continuous EMG signals into different levels of EMG representations spanning from continuous latent features to discrete tokens operating at 50 Hz. Trained on twelve public EMG datasets, MyoCodec achieves favorable performance in both intrinsic codec quality and representative downstream tasks, including typing (emg2qwerty), hand-pose (emg2pose), speech decoding (emg2speech), and speech-to-EMG synthesis (speech2emg). Across these tasks, MyoCodec exhibits strong performance against prior models while providing a compact and causal EMG representation. During streaming inference, it requires compute time of only 0.482 ms for each 20 ms frame, enabling real-time streaming. Also, the discrete token representation provided by MyoCodec has the potential to support integration into language-model based approaches, creating a path toward LLM-based interactive systems, where tokenized EMG representations are directly processed into such language or speech models. Code and model weights are released.

eess.SP↗

arXiv2026

Towards Interpretable Framework for Neural Audio Codecs via Sparse Autoencoders: Exploration toward Age, Gender, and Accent Steering

Neural audio codecs (NACs) are widely used in speech generation and audio-language modeling, yet how they encode speaker-trait information remains poorly understood. Prior work applied sparse autoencoders (SAEs) to investigate accent information in NACs through task-level analysis. Here, we extend this analysis to the waveform level and to age, gender, and accent, using SAE steering to probe trait-related information in sparse activations. We identify trait-associated dimensions, modify their activations, and evaluate the resulting reconstructed speech. Across five NACs, steering the selected dimensions induces target-directed shifts in speaker-trait predictions. A random-dimension baseline on Mimi produces smaller shifts, supporting the relevance of the selected dimensions. However, responses vary across codecs, traits, and steering directions, and increasing steering strength does not consistently amplify the intended shifts. Steering also generally increases word error rates and lowers predicted perceptual quality. These findings suggest that SAEs capture speaker-trait information in steerable activations, while the accompanying quality degradation highlights the need to better separate trait-related information from other information.

cs.SD↗

arXiv2026

Tracking Driving Stressors through Multimodal Physiological Monitoring

Understanding and mitigating driving stress is important for improving road safety and driver well-being. Reliable estimation, however, requires distinguishing biobehavioral responses to individual stressors from gradual physiological and contextual changes. We collected physiological data and vehicle telemetry from 31 participants across 44 simulated-driving sessions containing controlled stressor events. Under cross-validation, a multimodal classifier achieved an AUROC of 0.768 when distinguishing the stressor phase from an earlier baseline, reflecting both stressor effects and temporal drift. Controlling for drift retained an AUROC of 0.661, but revealed stronger responses to sustained than brief stressors, and shifted feature attribution toward phasic cardiac and electrodermal markers. We further quantified the interaction between model-estimated physiological stress and observable changes in vehicle control through simulation telemetry. Our findings show that stressor-aware modeling can identify physiologically grounded responses that correspond to meaningful changes in driving behavior.

eess.SP↗

arXiv2026

Speaker Role and Language Diarization for Analyzing Multilingual Interviews for Language Proficiency of Older Adults

Automatic language proficiency assessment in the context of multilingual interview-based settings remains underexplored. In this work, we develop Whisper-based speaker-role and language diarization systems to automatically extract respondent speech and characterize language usage in multilingual interviews with older adults. We further investigate whether diarization-derived conversational and language-use behaviors can support downstream language proficiency assessment. Results show that language-adapted Whisper models substantially improve language diarization performance for lower-resource and linguistically related Indian languages. Statistical analyses reveal that respondent speech ratio and intended language usage are strong predictors of proficiency ratings. Furthermore, simple diarization-derived behavioral features achieve performance comparable to Whisper-based speech embeddings for proficiency prediction, while combining both yields the best results. Importantly, both the speech and language use statistical analyses and language proficiency prediction performance remain largely preserved when using fully automatic diarization outputs, demonstrating the potential of respondent-centric conversational analysis for scalable language proficiency assessment.

eess.AS↗

arXiv2026

End-to-End Joint ASR and Speaker Role Diarization with Child-Adult Interactions

Accurate transcription and speaker role diarization of child-adult spoken interactions are crucial for developmental and clinical research. However, manual annotation is time-consuming and challenging to scale. Existing automated systems typically rely on cascaded speaker diarization and automatic speech recognition pipelines, which can lead to error propagation. This paper presents a unified end-to-end framework that extends the Whisper encoder-decoder architecture to jointly model ASR and child-adult speaker role diarization. The proposed approach integrates: (i) a serialized output training scheme that emits speaker tags and start/end timestamps, (ii) a lightweight frame-level diarization head that enhances speaker-discriminative encoder representations, (iii) diarization-guided silence suppression for improved temporal precision, and (iv) a state-machine-based forced decoding procedure that guarantees structurally valid outputs. Comprehensive evaluations on two datasets demonstrate consistent and substantial improvements over two cascaded baselines, achieving lower multi-talker word error rates and demonstrating competitive diarization accuracy across both Whisper-small and Whisper-large models. These findings highlight the effectiveness and practical utility of the proposed joint modeling framework for generating reliable, speaker-attributed transcripts of child-adult interactions at scale. The code and model weights are publicly available

eess.AS↗

arXiv2026

Smiling Regulates Emotion During Traumatic Recollection

We study when, where, and why 978 Holocaust survivors smile in video testimonies. We create an automatic smile detection model from facial features with an F1 of 85% and annotate detected smiles under two established taxonomies of smiling. We produce narrative features on 1,083,417 transcript sentences as well as emotional valence from three different modalities: audio, eye gaze, and text transcript. Smiling rates are associated with specific semantic topics, narrative structures, and temporal syntaxes across the corpus. Smiles often occur during periods of intense negative affect and we find negative-affect smiles are associated with more positive subsequent valence trajectories across all three modalities. Smiling reduces eye dynamics and blink rates, with both of these effects modulated by narrative valence. Taken together, we conclude that smiling plays a critical role in regulating emotion and social interaction during traumatic recollection.

cs.MM↗

arXiv2026

Towards Interpretable Framework for Neural Audio Codecs via Sparse Autoencoders: A Case Study on Accent Information

Neural Audio Codecs (NACs) are widely adopted in modern speech systems, yet how they encode linguistic and paralinguistic information remains unclear. Improving the interpretability of NAC representations is critical for understanding and deploying them in sensitive applications. Hence, we employ Sparse Autoencoders (SAEs) to decompose dense NAC representations into sparse, interpretable activations. In this work, we focus on a challenging paralinguistic attribute-accent-and propose a framework to quantify NAC interpretability. We evaluate four NAC models under 16 SAE configurations using a relative performance index. Our results show that DAC and SpeechTokenizer achieve the highest interpretability. We further reveal that acoustic-oriented NACs encode accent information primarily in activation magnitudes of sparse representations, whereas phonetic-oriented NACs rely more on activation positions, and that low-bitrate EnCodec variants show higher interpretability.

cs.SD↗

arXiv2026

Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs

Existing visual privacy benchmarks largely treat privacy as a binary property, labeling images as private or non-private based on visible sensitive content. We argue that privacy is fundamentally compositional. Attributes that are benign in isolation may combine to produce severe privacy violations. We introduce the Compositional Privacy Risk Taxonomy (CPRT), a regulation-aware framework that organizes visual attributes according to standalone identifiability and compositional harm potential. CPRT defines four graded severity levels and is paired with an interpretable scoring function that assigns continuous privacy severity scores. We further construct a taxonomy-aligned dataset of 6.7K images and derive compositional risk scores. By evaluating frontier and open-weight VLMs we find that frontier models align well with compositional severity when provided structured guidance, but systematically underestimate composition-driven risks. Smaller models struggle to internalize graded privacy reasoning. To bridge this gap, we introduce a deployable 8B SFT model that closely matches frontier-level performance on compositional privacy assessment

cs.CV↗

arXiv2026

Speech Codec Probing from Semantic and Phonetic Perspectives

Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. Speech tokenizers are expected to preserve both semantic and acoustic information for downstream understanding and generation tasks. However, emerging evidence suggests that the term "semantic" in speech processing does not align with linguistic lexical-semantic, leading to a mismatch between speech and text modality. In this paper, we systematically analyze the information encoded by several widely used speech tokenizers, evaluating their lexical-semantic and phonetic content through three tasks. Our results show that current tokenizers primarily capture phonetic rather than lexical-semantic structure, deriving practical implications for the design of next-generation speech tokenization methods. Code is released to public at https://github.com/Alexuan/codec_probing_release.

eess.AS↗