Papers for
call center operators
Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.
Contextual pictograms help fix speech transcription errors in French and Spanish
Contextual Pictograms for Repairing Multilingual ASR Errors
Abstract: Speech transcription errors can be difficult to recognize when competing word hypotheses are unfamiliar or visually similar. We describe an interface that combines alternative transcripts, replay and contextually checked pictograms for selected uncertain concepts. The system will initially support French and Spanish functional utterances. A counterbalanced study will assess whether pictorial feedback helps listeners recover the speaker's intended action beyond text alternatives alone. We will also quantify semantic mismatch and additional interaction time, since an inappropriate image can reinforce the wrong interpretation rather than repair it.
Interface Quilt creates patches to change app interfaces without code
Interface Quilt: Modifying Applications with Computer Use Agents and Generative UI
Abstract: Modifying an existing application is difficult when it does not provide programmatic access for that change. Recent advances in computer-use agents (CUAs) enable richer understanding and operation of existing interfaces, while generative UI (GenUI) makes it practical to generate new ones. We examine how these advances expand software modification through a design space of what can be changed and a framework for how modifications can be implemented. We then introduce Interface Quilt, a system that combines CUAs and GenUI to generate interface patches, which are new interfaces displayed over an existing application to modify its presentation, interaction, and capabilities. Through demonstrations across a variety of applications, we show that interface patches support a range of modifications without source code, APIs, or accessibility data.
Streaming system protects voice privacy and removes personal info fast
Toward Complete Speaker Anonymization: a Streaming Cascaded System for Voice Privacy and PII Removal
Abstract: We present a cascade streaming voice privacy system, consisting of ASR, NLP, and TTS modules. By leveraging recent improvements in all three aspects of speech and language processing, we show that such a system is capable of achieving a result comparable to state-of-the-art offline voice privacy systems, while providing controllable capabilities of content protection beyond voice. With an estimated utterance-onset end-to-end latency of 717 ms, the presented system preserves speech content with 11% WER on Librispeech, while detecting PII with a 69% SLU F1 score and achieving up to 47.66% EER against a semi-informed attacker.
Voice anonymization keeps speech clear and identity safe
The Content Leash: Mitigating Degenerate Solutions in Invertible Speaker Anonymization
Abstract: 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.
Speaker diarization improved for live and recorded audio
S2SND-v2: Unified Online and Offline Speaker Diarization with Speaker-Adapted w2v-BERT 2.0
Abstract: This paper presents S2SND-v2, a unified online and offline speaker diarization framework built on S2SND that improves acoustic feature extraction and the use of the resulting representations. For acoustic feature extraction, we introduce a speaker-adapted w2v-BERT 2.0 front end and compare full and pruned construction routes. To better use these features, overlap-aware activity-query masking improves speaker embedding extraction under overlap, while late-speaker training aligns unknown-speaker training with online inference conditions. Combining these improvements, the pruned system achieves competitive average diarization error rates of 14.52% online and 12.03% offline across eight test sets.
Speech enhancement improved by noisy target training with drifting loss
Noisy Target Training Meets Drifting for Weakly-Supervised Speech Enhancement
Abstract: In speech enhancement, standard supervised training requires pairs of noisy and clean speech. Such pairs are typically created by artificially degrading clean speech, leading to a domain mismatch between synthetic training data and real recordings. Noisy target training (NyTT) mitigates this limitation by training an enhancement model to predict a noisy recording from a noisier version generated by adding extra noise. However, since the training target is noisy, NyTT might learn to leave residual noise in the enhanced output. In this paper, we address this issue in NyTT by incorporating a Sinkhorn drifting loss that matches the distribution of the enhanced speech to that of unpaired clean speech. The Sinkhorn drifting loss attracts enhanced speech toward high-density regions of the clean-speech distribution while repelling it from the current enhanced-speech distribution in latent space. This loss uses only unpaired clean speech rather than the clean counterpart of each degraded recording, preserving the weakly-supervised nature of NyTT. Experimental results on VoiceBank-DEMAND and CHiME-3 real recordings demonstrate the efficacy of the proposed combination.
Target speech extraction works better with music in the background
MuseFlow-TSE: Music-Aware Target Speech Extraction via Cross-Source Band-Splitting and Data-to-Data Flow Matching
Abstract: Target speech extraction (TSE) isolates a speaker's voice given an enrollment utterance, but existing work is validated almost exclusively without music. Discriminative methods are content-faithful yet masking-bounded; generative methods improve naturalness but may hallucinate, drift in identity, and require many steps. We present MuseFlow-TSE, a discriminative deletion, generative insertion framework for music-bearing scenes. Stage-1 is a music-aware cross-source band-split extractor that estimates target, interfering speakers, music, and noise under conservation and music-leakage constraints. Stage-2 is a data-to-data flow refiner initialized by the discriminative estimate, negatively conditioned on interference stems, and run for 1--4 difficulty-adaptive Euler steps with an end-to-end fidelity objective.
Soloist separates voices from noisy and overlapping speech
Soloist: A Generative Model for Blind Voice Separation in the Wild
Abstract: Real-world voice separation must recover individual voices from overlapping speech, environmental noise, and music, yet isolated source recordings are rarely available for supervision. We introduce Soloist, a generative model for blind voice separation that autoregressively generates individual voice streams as audio-codec sequences conditioned on the mixture, without requiring a target-speaker query or a predefined voice count. We propose a two-stage training paradigm to learn from synthetic mixtures and adapt to real recordings. The first stage combines supervised separation on synthetic mixtures with isolated source targets and an auxiliary task that predicts speaker timelines from real recordings, learning who speaks when from natural acoustics. The second stage applies reinforcement learning to real recordings, with rewards supplied by a model judge that compares candidate separations based on voice purity and content preservation without isolated source targets. Across diverse scenarios, Soloist recovers clean speech from multi-speaker overlap and noisy recordings, and extracts singing vocals from music accompaniment while maintaining relatively high pitch accuracy and intelligibility. On real-world recordings with unknown voice counts, Soloist also separates voices well. Finally, we integrate Soloist into a full-duplex conversation processing pipeline that assembles separated outputs into continuous speaker tracks, demonstrating its practical utility in real conversations.
HINTT compares cascaded and unified speech models for multilingual diarization and transcription
HINTT Submission to the 2nd MLC-SLM Challenge: Comparing Cascaded and Unified Approaches to Diarization and ASR
Abstract: This paper presents the HINTT system submitted to the 2nd Challenge and Workshop on Multilingual Conversational Speech Language Model (MLC-SLM). We address multilingual speaker-attributed ASR, where systems must determine who spoke when and what was spoken. We investigate two modeling strategies for this problem: a cascaded pipeline that combines speaker diarization with speech-LLM-based ASR, and a unified speech LLM that directly generates speaker labels, timestamps, and transcriptions. Our final submission is based on the cascaded pipeline, consisting of a fine-tuned DiariZen diarization model, a fine-tuned Qwen3-ASR model, and LLM-based generative error correction. For comparison, we also fine-tune VibeVoice-ASR as a unified model using the same official training data. All task-specific fine-tuning and model selection are performed using only the official MLC-SLM data, without external data or pseudo-labels. Experimental results demonstrate that the cascaded system remains more reliable under the MLC-SLM Task 1 conditions, while unified speech LLMs offer a promising direction for future speaker-attributed ASR.
Nonpreemptive scheduling learns job service speeds to cut queue length
Nonpreemptive Scheduling While Learning Context-Dependent Service Rates
Abstract: We study nonpreemptive contextual queueing bandits in a single-server system. Each job is represented by a $d$-dimensional context vector; in each round, a job may arrive with its context drawn from an unknown distribution $\mathcal{D}$, and its departure probability is determined by a logistic model of that context vector with an unknown parameter $θ^*$. The server learns from service outcomes while deciding which waiting job to serve and whether to idle, aiming to minimize queue-length regret, the gap between its expected terminal queue length and the minimum achievable by an admissible policy. Once selected, a job must be served until completion, and we refer to this as the nonpreemptive setting. A central challenge is that, even with full model knowledge, the optimal policy cannot in general be characterized by a simple myopic rule, since the optimal action can change with the remaining horizon at the same queue state. Nevertheless, when the model and horizon are known, the optimal action can be obtained through a finite-horizon Bellman recursion. Motivated by this, we propose Learn--Clear--Plan (LCP), which estimates the system and uses the resulting Bellman recursion to make horizon-dependent decisions. LCP achieves $\widetilde{O}(\sqrt{d/T})$ queue-length regret, while a lower-bound construction gives $Ω(\min\{1/\sqrt{d},\sqrt{d/T}\})$ regret for every learning policy on some instance, establishing optimality up to polylogarithmic factors when $T\ge d^2$. When the horizon is unknown, no horizon-independent policy achieves vanishing regret against the finite-horizon optimum. We therefore use SEPT, the policy that serves a waiting job with the highest probability of departure, as a fixed reference, and suggest an estimated-SEPT algorithm that achieves a tracking error of $\widetilde{O}(\sqrt{d/t})$ without knowing the model.
Speech deepfake detection improves using combined acoustic features
What Survives the Codec Shift: Pooled No-Vocals Residuals for Speech Deepfake Detection
Abstract: The transition from vocoder-based to neural-codec speech synthesis makes generalization more difficult for speech deepfake detectors, particularly those relying on speech-oriented representations. It remains unclear which acoustic representations retain discriminative information when the generation mechanism changes. We therefore compare 12 acoustic representations using a shared low-capacity linear classifier to identify effective evidence under codec shift. The analysis shows that hierarchical XLS-R leads on the pooled test set, while pooled no-vocals residual statistics perform best on the unseen-codec condition, revealing complementary behavior across generation conditions. Building on this finding, we propose MN-P, a dual-view detector that integrates an utterance-level pooled no-vocals representation with token-level XLS-R features through adaptive gating. The proposed MN-P reduces EER by 54.2% overall and by 60.9% on the codec-unseen condition relative to the best-performing retrained state-of-the-art system, with consistent gains across different detector backends. These results indicate that pooled no-vocals residual statistics provide effective complementary evidence for cross-generation speech deepfake detection.
Speaker temporal memory improves multi speaker speech recognition accuracy
STAM-ASR: Speaker-Temporal Anchoring with Memory for Multi-Speaker ASR
Abstract: Natural conversations make both speech recognition and speaker attribution challenging for ASR, as speakers take turns, overlap, and reappear over time. We propose STAM-ASR, Speaker-Temporal Anchoring with Memory, a lightweight framework that extends an already pretrained AudioLLM for multi-speaker ASR. Without relying on an external diarization system, STAM-ASR learns speaker activity and speaker-aware representations directly from intermediate AudioLLM features. Hence providing explicit who and when cues to modulate the AudioLLM's semantic representation without explicit speech separation. STAM-ASR further maintains fixed-size speaker and conversational memories to carry complementary context across turns. We evaluate STAM-ASR on AMI, ICSI, LibriCSS, and NOTSOFAR-1 across close-talk, far-field, overlapping, and cross-domain conditions. Our reported results shows that speaker-temporal conditioning and memory provide complementary benefits, while the gap between reference and predicted speaker activity identifies robust speaker tracking as a key remaining challenge.
Speech enhancement model improves transcription accuracy on real recordings
Transcript-Supervised Post-Training of Generative Speech Enhancement on Real Recordings via Reinforce Adjoint Matching
Abstract: We adapt Reinforce Adjoint Matching (RAM), a reward-based post-training method, to generative speech enhancement (SE). Starting from a pretrained SE model, RAM tilts the model's conditional distribution toward outputs with higher reward. During training, the current model generates enhanced speech on-policy, evaluates each generated endpoint with a potentially non-differentiable reward, and analytically re-noises the endpoint to construct inputs for a reward-guided regression objective. This enables post-training directly on real recordings using weak supervision, such as text transcripts, without requiring paired clean speech targets or reward gradients. We investigate word error rate (WER)-based post-training and whether recognition performance can be improved without compromising perceptual speech quality. Experiments on real CHiME-4 recordings reduce WER by 5.08 percentage points relative to pretrained FlowSE without reducing any of the reported non-intrusive speech quality metrics. A subjective listening test at the default reward scale finds no statistically significant preference between the post-trained and pretrained models.
Multilingual challenge advances conversational speech recognition and understanding
The Second MLC-SLM Challenge: Multilingual Conversational Speech Diarization, Recognition, and Understanding
Abstract: This paper summarizes the Interspeech2026 second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge, which aims to advance the development of effective multilingual conversational speech language models. We describe the two challenge tasks: multilingual conversational speech diarization and recognition, and multilingual conversational speech understanding, together with the released real-world conversational speech dataset, evaluation protocols, and baseline systems. The challenge attracted 91 teams worldwide, with 704 valid leaderboard results and 14 technical reports across the two tasks. Based on the participating systems, we summarize representative approaches and distill practical insights into multilingual conversational speech recognition and understanding to support future research in the community.
Small language model quickly detects scam calls with calibrated confidence
Open-Jev Judgments on CallScreenBench: Calibrated One-Pass Scam Screening with a Small Language Model
Abstract: Screening a phone call for fraud needs a trustworthy probability after every caller turn, in milliseconds. Jev-style typed decisions promise exactly that: declared options go in, one calibrated probability per option comes out of a single forward pass, with no generated text. We test an open implementation of this readout, JevLite, on scam-call screening: Qwen3-4B is LoRA-tuned so that the temperature-scaled softmax over two answer-label logits is P(scam). On 41 held-out CallScreenBench scenarios (577 per-turn decisions) a three-seed ensemble reaches AUROC .974 with calibration error .052, non-inferior to an LLM judge (MiniMax-M3) at a pre-registered .02 margin, with no false alarms on legitimate calls, decisions 1.14 turns earlier under the same hang-up rule, and 64.5 ms per decision on one consumer GPU, 4.9x lower than the same backbone fine-tuned to generate its answer. The gain is in the readout and calibration, not accuracy: a fine-tuned ModernBERT encoder is not significantly worse, the recipe was selected with test-set exposure, and all callers are synthetic. We claim no architectural novelty; the contribution is the application and an evaluation reporting calibration, false alarms and decision timing alongside AUROC.
Style aware paraphrasing reduces text authorship identification risks
I Am No One: Style-Aware Paraphrasing for Text Anonymization
Abstract: Authorship attribution models can re-identify users from seemingly anonymized text by exploiting stable stylistic fingerprints, even after explicit identifiers are removed, posing a growing privacy risk for text publishing and analytics. This risk extends to speech-derived text such as ASR transcripts of meetings and call-center conversations, where stylometric leakage can persist even after acoustic anonymization. Differential privacy-based anonymization often severely degrades text quality and utility. We propose a style-aware, prompt-driven anonymization approach that uses pretrained large language models to construct compact stylistic profiles from minimal samples and rewrite text to suppress identifiable style markers while preserving meaning. Across blog and review datasets, our approach reduces authorship attribution F1 by 60-70% while maintaining content quality and readability, substantially outperforming DP-based and non-DP baselines.
Qwen audio 3.0 ASR system recognizes diverse languages and dialects
Qwen-Audio-3.0-ASR Technical Report
Abstract: In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling, model scaling, and deep integration with large language models (LLMs). However, bridging the gap between academic benchmark performance and real-world production utility remains a persistent challenge, particularly in handling diverse regional dialects, dynamic entities and hotwords, long-range contextual information, and disfluent spontaneous speech. In this report, we present Qwen-Audio-3.0-ASR, a Mixture-of-Experts (MoE) LLM-based ASR system designed to address these production demands through a unified, instruction-following framework. The model is built upon the Qwen backbone, and is trained on tens of millions of hours of large-scale speech data. Qwen-Audio-3.0-ASR supports transcription across 30 languages and 16 Chinese dialectal varieties spanning eight major dialect regions. Beyond multilingual and dialectal recognition, the model provides production-oriented capabilities including industry-domain entity recognition, hierarchical hotword customization, native single-pass transcription polishing, and long-audio contextual modeling. We further develop a dedicated streaming variant, Qwen-Audio-3.0-ASR-Streaming, for latency-sensitive applications. Extensive evaluations on Chinese, English, multilingual, and real-world industrial test sets demonstrate state-of-the-art or highly competitive recognition performance across a broad range of evaluation conditions, with strong performance relative to leading commercial and proprietary systems including GPT-4o Transcribe and Gemini 3.1 Pro.