46 articles mentioning speaker-diarization-community-1
arXiv:2610.26929v1 Announce Type: cross Abstract: Sanskrit verse recitation is governed by $\textit{Chandas}$, a strict prosodic framework defined by rhythmic $\textit{Laghu}$ (light) and $\textit{Guru}$ (heavy) syllables. Because existing Sanskrit speech datasets prioritize ASR or conversational TT
arXiv:2610.28053v1 Announce Type: cross Abstract: This paper presents a causal, training-free linker that allows a frozen streaming diarizer to track more speakers than it has output slots. Streaming end-to-end diarizers such as Streaming Sortformer emit a fixed number N of concurrent speaker slots.
arXiv:2610.27210v1 Announce Type: new Abstract: Speech models are increasingly used as an interface to AI systems, from transcription tools to voice agents. Existing audio backdoors require an attacker to introduce triggers at inference time. We study a different threat model in which the attacker c
arXiv:2610.27109v1 Announce Type: cross Abstract: Spoken interaction is moving from alternating turns to full-duplex conversation, where an agent listens while speaking. Learning this coordination requires natural dialogue with persistent speaker-resolved tracks, a data requirement that remains diff
arXiv:2610.12474v3 Announce Type: replace-cross Abstract: Zero-shot text-to-speech (TTS) can clone a voice from seconds of audio. Yet the quality comes from billion-parameter diffusion transformers whose size and multi-step sampling put them out of reach of the on-device, assistive, and real-time ap
arXiv:2610.20327v2 Announce Type: replace Abstract: India's 22 scheduled languages are spoken by over a billion people in conversations that mix languages, often within one turn, overlap freely, and take place over telephones, in meetings, and in media. Knowing who spoke when, the task of speaker di
arXiv:2610.21773v1 Announce Type: cross Abstract: Audio-visual speech enhancement (AVSE) leverages visual cues to recover target speech from mixtures corrupted by reverberation, noise, and overlapping speakers. We propose a coarse-to-fine two-stage AVSE framework. In the first stage, a progressive S
arXiv:2610.22163v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly being adopted as teaching tools in computing education, particularly for developing AI tutors capable of answering student questions. With the rise in enrollment of international students in computing progr
arXiv:2610.13440v1 Announce Type: cross Abstract: Recent accent classification systems can achieve high accuracy in standard in-corpus evaluations. However, when speakers overlap between the training and test sets, such results may overestimate model robustness compared with real-world deployment sc
arXiv:2610.11825v1 Announce Type: new Abstract: Detecting intra-operative speech impairment during awake craniotomy is essential for preserving language function. However, automated detection remains challenging because operating-room recordings contain substantial acoustic interference, clinically
arXiv:2610.08107v1 Announce Type: cross Abstract: Attacker ASV systems for voice anonymization have been studied primarily in English, leaving their behavior in multilingual settings largely unexplored. Conventional ASV has shown that both acoustic and contextual information are important for multil
arXiv:2610.10208v1 Announce Type: cross Abstract: Automatic audio scene description turns a recording into a text account of a situation. One difficulty is deciding which elements of the audio should be kept, since a description cannot include them all. Annotators disagree about this, making a groun
arXiv:2610.03017v1 Announce Type: new Abstract: This work presents an automatic speech recognition (ASR) system personalized for a Czech speaker with a permanent tracheal stoma and severe dysarthria rendering their speech unintelligible to untrained listeners. We release a public dataset containing
arXiv:2610.02941v1 Announce Type: cross Abstract: Real-time conversational agents require speaker diarization that streams and runs on a CPU. Most systems apply an utterance-level speaker encoder to short, heavily overlapping chunks, which wastes computation and leaves the model optimized for the wr
arXiv:2609.33212v2 Announce Type: replace Abstract: Speaker verification systems achieve high accuracy but provide little account of the acoustic evidence behind their judgments. Making these systems inspectable requires exposing interpretable evidence while retaining the richer information on which
arXiv:2609.38491v1 Announce Type: new Abstract: Clinical research in psychiatry increasingly relies on large scale collection of spoken language data to identify acoustic and linguistic biomarkers. Yet evolving consent and protocol requirements can oblige investigators to remove a designated speaker
arXiv:2609.39162v1 Announce Type: cross Abstract: Speaker diarization systems based on speaker embeddings and neural diarization exploit complementary forms of speaker information, but their intermediate representations are not directly compatible. We introduce Training-Free Affinity Fusion (TFAF),
arXiv:2609.39344v1 Announce Type: cross Abstract: Speech transcripts used as long-term memory must preserve both words and stable speaker identities. Existing meeting-transcription metrics either ignore speakers or remap anonymous speakers independently in each recording, so they cannot measure whet
arXiv:2609.39088v1 Announce Type: cross Abstract: Long-form live-streaming TTS requires context-dependent prosody and paragraph-level coherence. However, many existing instruction-based TTS systems use global or uniform conditions, providing limited explicit control over clause-level relative prosod
arXiv:2609.38964v1 Announce Type: new Abstract: Multi-agent debate (MAD) is often used to improve large language model (LLM) reasoning, but sequential debate is rarely a neutral aggregator of agents' opinions. We show that sequential MAD suffers from a pronounced first-speaker bias: agents dispropor
arXiv:2609.36500v1 Announce Type: cross Abstract: Speaker verification systems encounter combinations of noise, channel distortion, and changes in speech. Evaluating each condition separately does not establish whether their effects add. InterBias-SV organises this question around a four-term compar
arXiv:2609.15203v2 Announce Type: replace-cross Abstract: Speaker recognition neural networks recognise speaker identities from input utterances by learning latent representations (i.e. speaker embeddings). However, these networks' internal mechanisms remain largely opaque, motivating research in ex
arXiv:2609.11182v2 Announce Type: replace-cross Abstract: In traditional pattern recognition tasks, neural networks are trained to recognise human-defined patterns (e.g. audio categories) in model inputs (e.g. audio). Meanwhile, some Explainable AI (XAI) methods explain latent patterns characterisin
arXiv:2609.30439v1 Announce Type: new Abstract: We introduce target-speaker unlearning ASR (TSU-ASR) task in a fully end-to-end framework for multi-speaker ASR and diarization. Given a multi-speaker utterance and a set of opt-out speakers who do not wish to have their speech transcribed, the task re
arXiv:2609.30476v1 Announce Type: cross Abstract: Target-speaker automatic speech recognition (TS-ASR) must identify and transcribe a desired speaker under varying overlap and noise conditions. These changes alter the acoustic evidence for the target speaker in the speech mixture, motivating inferen
arXiv:2509.18377v3 Announce Type: replace Abstract: Most automatic speech processing systems operate in ``open loop'' mode without user feedback about who said what, yet human-in-the-loop workflows can potentially enable higher accuracy. We propose an LLM-assisted in-meeting speaker correction syste
arXiv:2609.29766v1 Announce Type: cross Abstract: Cross-speaker acoustic-to-articulatory inversion requires accounting for anatomical differences between speakers. We propose a geometric adaptation framework that uses anatomical landmarks, primarily on vertebrae and dental structures,to transfer pre
arXiv:2609.29123v1 Announce Type: cross Abstract: In cross-lingual zero-shot text-to-speech, the accent of the reference leaks into the target speech. We propose accent analogy guidance (AAG), a training-free sampler term that subtracts an accent direction estimated from the model's own predictions
arXiv:2609.27399v1 Announce Type: cross Abstract: Recent zero-shot text-to-speech (ZS-TTS) systems can reproduce a speaker's voice with high fidelity from only a few seconds of reference speech, raising concerns over unauthorized voice cloning and impersonation. Speaker identity unlearning has recen
arXiv:2609.25007v1 Announce Type: cross Abstract: The performance of state-of-the-art speaker verification (SV) systems severely degrades on short utterances due to insufficient speaker-specific information. To address this critical challenge, we propose the Vector Archive Mapping ECAPA (VAM-ECAPA),
arXiv:2609.26780v1 Announce Type: new Abstract: Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distinguish who said what, whom each statement concerns, how individuals perceive one another, what information
arXiv:2609.24061v1 Announce Type: cross Abstract: In this paper, we propose MECT, a speaker verification model that integrates the Mixture-of-Experts (MoE) mechanism into a CNN-Transformer backbone with optimized block structure and stacking scheme. Specifically, we investigated four MoE variants th
arXiv:2609.25948v1 Announce Type: cross Abstract: Target-speaker and multi-speaker extraction are techniques for extracting speech from a desired speaker or desired speakers in the presence of other speakers and/or noise. Neural network approaches for this task are often trained and evaluated using
arXiv:2609.24812v1 Announce Type: new Abstract: Voice provides a natural and immediate interface for AI agents. Many settings in which voice agents could be useful, including meetings, households, and collaborative work, are inherently multi-speaker. Supporting these settings introduces challenges t
arXiv:2609.20833v1 Announce Type: new Abstract: This paper presents the Transsion Speech Team submission to Task 1 of the MLC-SLM 2026 Challenge, which focuses on speaker-attributed transcription for multilingual conversational speech. We propose a cascaded framework consisting of three components:
arXiv:2609.20232v1 Announce Type: new Abstract: We introduce the \textbf{Public Discourse Corpus (PDC)}, the first dataset of public-figure interview speech jointly annotated for affective valence and epistemic modality. The corpus contains 998 videos from 100 speakers across seven professional doma
arXiv:2609.18673v1 Announce Type: cross Abstract: Speaker de-identification (SDID) aims to preserve privacy by concealing speaker identity while maintaining speech utility. However, current evaluations often reduce privacy to a single dimension - biometric verification performance - typically measur
arXiv:2601.09050v2 Announce Type: replace Abstract: Tonal low-resource languages are widely spoken but remain underserved by modern speech technologies. A central challenge is learning speech representations that are robust to nuisance variation, such as speaker gender, while preserving lexical tone
arXiv:2609.16275v1 Announce Type: new Abstract: Charismatic speech is shaped by language and speaking style, yet their relative contribution in bilingual public speaking remains unclear. We analyzed spontaneous speeches of 10 politicians who address audiences in Luxembourgish and French, in highly c
arXiv:2503.05794v4 Announce Type: replace-cross Abstract: Speaker verification models are trained on large-scale public datasets whose licenses usually prohibit unauthorized commercial use, yet such infringement is difficult to detect or deter. Dataset ownership verification (DOV) is the mainstream
arXiv:2609.16274v1 Announce Type: new Abstract: Speech rhythm helps structure persuasive speech, but most empirical work examines monolingual English. This study asks how politicians organize timing when speaking Luxembourgish and French. We analyze 400 sentences from ten politicians, annotated for
arXiv:2603.07551v3 Announce Type: replace-cross Abstract: Recent zero-shot Text-to-Speech (TTS) systems can clone previously unseen voices from only a few seconds of audio. We formulate Speech Generation Speaker Poisoning (SGSP), a task that seeks to prevent a model from synthesizing targeted speake
arXiv:2510.10774v4 Announce Type: replace-cross Abstract: Persian remains substantially underrepresented in open speech-text resources, limiting progress in multi-speaker text-to-speech (TTS), speech-language modelling, and low-resource speech processing. We introduce ParsVoice, the largest publicly
arXiv:2602.08696v3 Announce Type: replace-cross Abstract: Dysarthric speech recognition is limited by high speaker variability and scarce labeled data. Existing synthesis methods often couple speaker identity with dysarthric articulation, reducing control over generated speech. We propose a controll
arXiv:2607.21820v2 Announce Type: replace-cross Abstract: Audio deepfake detectors are trained to distinguish genuine speech from synthetic speech and often perform well on standard benchmarks. Yet the same detector that achieves less than 1% error on one dataset can see its error rate increase twen