Speech
-
Tracing and Relearning Detection Evidence in Text-to-Speech Systems
2026-09-25 08:29:14Eunji Shin, Kyudan Jung, Jihwan Kim, Minwoo Lee, Jaegul ChooAbstract
Recent audio deepfake detectors separate bona fide speech from synthetic speech, yet it remains unclear which stage of a text-to-speech system supplies the detection evidence. We address this with controlled resynthesis and detector adaptation in an F5-TTS-BigVGAN pipeline. Since vocoder reconstruction of a real mel can itself be separable from the source utterance, we fix the vocoder and trace the larger change in detector separation to acoustic generation. Adversarially fine-tuning the acoustic model, with no detector in its objective, raises EER against fixed detectors at comparable quality. However, adapting a detector only on the tuned model's VCTK outputs lowers its LibriSpeech EER from 19.42% to 7.46% and improves detection of unseen base F5-TTS outputs. These results suggest that acoustic-model updates can reduce the detection evidence available to fixed detectors, while detector adaptation keeps the updated outputs detectable in this pipeline.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30983
PDF
-
A Comprehensive Study of Content Representations for Speech Synthesis
2026-09-25 08:20:56Diego Torres, Axel Roebel, Nicolas ObinAbstract
Speech content representations are central to voice conversion, speech-to-speech translation, and multimodal language models, yet they are rarely compared under a common generative framework that directly measures what each representation contains. We address this by training a generative model conditioned solely on each representation and evaluating the generated audio along the content, speaker identity, and prosody axes. Across SSL features, supervised tokens, posteriorgrams, and neural audio codecs, we find two distinct regimes: representations that nearly reconstruct the original audio, and representations that effectively disentangle speaker identity. These results show that disentanglement depends not on supervision alone, but on the interaction between the training objective and the representation's information capacity: supervised representations only disentangle speaker identity when their capacity is sufficiently constrained.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30975
PDF
-
Where and When to Force: Routed Forcing for Streaming Avatars
2026-09-25 08:15:11Zihan Su, Siwen Lu, Junhao Zhuang, Zeyue Xue, Haoyang Huang, Guanghao Li, Xiaofeng Tan, Chun Yuan, Nan DuanAbstract
Audio-driven streaming avatar generation requires real-time synthesis of speech-synchronized videos with dynamic and diverse motion. Self Forcing uses Distribution Matching Distillation (DMD) to distill bidirectional video diffusion models into causal, few-step generators for real-time streaming. However, DMD minimizes a reverse KL divergence, which is inherently mode-seeking: it causes the student to discard high-dynamic modes and collapse onto static outputs, compressing both dynamics and diversity of generated videos. We find that this collapse is region-heterogeneous: person regions involving pose and gesture variations suffer the largest diversity loss, the audio-driven mouth region shows a small loss, and the background remains nearly stable. Based on this observation, we propose Routed Forcing, which routes the distillation objective by semantic region and noise stage to improve dynamics and diversity while preserving visual quality. Specifically, (1) Where to Force: Semantic-Region Routing applies Data-Forcing Distillation (DFD), which supervises the student with real videos, to the person region where diversity collapse is most severe, while retaining DMD for the mouth and background to preserve lip synchronization and scene stability. (2) When to Force: Noise-Stage Routing activates DFD at high noise stages, where real video serves as effective supervision to inject diverse and dynamic motion patterns. At low noise stages, DMD is used to refine details, avoiding blur and artifacts from spatial differences between real video and student-generated video. Experiments show that Routed Forcing improves dynamics by up to 45% and diversity by 7-25% over Self Forcing, while preserving video quality and lip synchronization.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30963
PDF
-
Training-Free Pronunciation Transcription via Text-Constrained Acoustic Rescoring
2026-09-25 07:38:49Hikaru Asano, Yotaro Kubo, So KurokiAbstract
Accurate and efficient pronunciation transcription is essential for preparing text-to-speech training data at scale. Existing approaches have different limitations: grapheme-to-pronunciation (G2P) and speech-to-pronunciation (S2P) methods each capture only partial information, using only text or only speech, while speech-and-text-to-pronunciation (ST2P) methods use both but require costly pronunciation-annotated data. To address this problem, we propose a training-free ST2P pipeline that integrates both lexical and acoustic information at inference time. Lexical resources and G2P tools generate text-constrained candidates, and a left-to-right greedy search selects the best one using whole-sequence negative log-likelihoods from frozen pretrained S2P models. On three Japanese corpora, our method reduces Character Error Rate (CER) from 0.60--1.40\% (text-only baseline) to 0.04--0.17\% with reference transcripts, and 0.64--1.58\% with ASR transcripts. It outperforms all baselines, including a trained ST2P model and commercial multimodal LLMs. Our greedy search method is 3--3.5$\times$ faster than beam search at similar CER, and the cascade is 2$\times$ faster than direct decoding ensuring the efficiency and accuracy. In Spanish, French, and preliminary English, it also surpasses four open multimodal LLMs and the best traditional methods.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30924
PDF
-
I-Parakeet: Integer-Only Conformer ASR on Mobile NPU
Abstract
In this paper, we propose I-Parakeet, an integer-only implementation of NVIDIA's Parakeet-CTC (0.6B parameters) that runs on a smartphone NPU without any floating-point operator or CPU fallback. Modern Conformer ASR models are hard to deploy on edge devices because of their size, and quantized models still fall back to floating point for numerically sensitive operations. This prevents them from fully exploiting integer accelerators such as mobile NPUs. To achieve this, our contributions are threefold. First, we derive an integer formulation of the relative-positional self-attention at the core of the Conformer. We fuse its two score branches with different quantization scales and the relative shift into integer-only operations. Second, we introduce a minimax-optimized Swish approximation that minimizes the maximum error of the Swish output. Third, a layer-wise range analysis of activations yields two targeted remedies: an INT16 grid for the BatchNorm output and percentile calibration for the heavy-tailed pre-encoder activations. I-Parakeet achieves 4.97% WER on LibriSpeech test-other, running on a Qualcomm NPU at a real-time factor of 0.048, 7.5x faster than a CPU baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30846
PDF
-
Subject-Invariant Cross-Modal Decoding of Perceived Speech from Brain Recordings
Abstract
Perceived speech decoding based on non-invasive brain-computer interface (BCI) signals has been extensively studied in recent years. Research in this field primarily faces two challenges: extracting neural representations with rich spatiotemporal information and achieving cross-subject generalization. Although separate studies have proposed methods to cope with these issues, a unified approach that simultaneously tackles both challenges remains lacking. To fill this gap, we propose the Subject-Invariant Cross-Modal Perceived Speech Decoding (SICMD) method, which integrates functional magnetic resonance imaging (fMRI) and magnetoencephalography (MEG). We conduct comprehensive analyses of the fusion method, fusion position, encoder architecture, and model inputs. Our results demonstrate that the proposed method improves Top-1, Top-10, and Rankacc by more than 10.6%, 10.1%, and 1.7%, respectively, compared to baseline methods in cross-subject perceived speech decoding tasks, while reducing training costs by 88.8% and 60.5% compared to multi-subject and intra-subject decoding settings. Further visualization experiments also confirm the effectiveness of our approach.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30832
PDF
-
Evaluating Real-Time Voice Agents: From Component Quality to Grounded Outcomes
2026-09-25 04:22:20Shivam Negi, Arpit Rawat, Rashi JainAbstract
Real-time voice agents have moved from research prototypes to production deployments, yet the literature describing them is fragmented across three communities that rarely cite one another: speech foundation modelling, turn-taking psycholinguistics, and agentic evaluation. Architecture papers report latency, turn-taking papers report prediction accuracy, and agentic benchmarks report task success, so no single number describes whether a deployed agent is actually good. We address that gap with three evidence-based claims, each traceable to a corpus of 38 primary sources organised into an application-centric taxonomy of six categories. First, architecture choice is a deployment constraint rather than a settled verdict: a 2026 enterprise tutorial reports that no fully self-hostable end-to-end system yet meets production constraints, while a chunked cascade independently reaches state-of-the-art duplex behaviour, showing duplex behaviour is separable from duplex architecture. Second, evaluation has shifted decisively from component quality toward grounded outcomes, with recent benchmarks verifying backend state rather than trusting what the agent claims to have done. Third, the dyadic assumption in most models and benchmarks is breaking down: multiparty turn-taking and multi-speaker reasoning benchmarks show that deciding when not to speak, and reasoning about who may be told what, are first-class capabilities two-participant framings cannot measure. For each source we state the problem it targets, its mechanism, and its reported evidence, alongside the search strategy, inclusion criteria, and a verification step that caught a misattributed arXiv identifier in circulation. We propose TRG (Timing-Recovery-Grounded), a reporting standard characterising an agent by timing, post-disruption recovery, and state-verified outcome together, with a conditional fourth axis for multiparty deployments.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30798
PDF
-
Symbiotic Architecture for Post-Hoc Audio Extension of Frozen Language Models
2026-09-25 04:06:01Yotaro Kubo, Qi Sun, Yujin TangAbstract
This paper proposes an architecture for equipping large language models (LLMs) with audio-understanding capabilities without fine-tuning their weights. The proposed symbiotic architecture employs an injector module that writes audio-conditioned vectors directly into the target LLM's short-term memory, i.e., the key-value (KV) cache, enabling the LLM to behave as an audio language model (ALM). The architectural advantages are twofold. First, it improves the scalability of ALMs: because the proposed method bypasses the LLM during audio injection, the injection cost is governed by the injector width rather than the backbone width, and can therefore scale more slowly than the cost of full-backbone prefilling. Second, since the training scheme does not update the LLM weights, the original capabilities of the LLM are preserved without the risk of degradation from fine-tuning. The effectiveness of the proposed method is evaluated on both audio-understanding tasks (automatic speech recognition, audio question answering, and acoustic scene classification) and text-only tasks. We confirm that, while activating fewer parameters during audio prefilling, our architecture outperforms the conventional method with a frozen LLM and approaches the performance of a fine-tuned ALM, all while preserving the backbone LLM's original text-only task performance by construction.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30784
PDF
-
Dialogue-Based Streaming Audio-Visual Target Speaker Extraction with Predictive Dialogue Information
2026-09-25 03:56:44Shuhan Zhang, Wenxuan Wu, Haizhou LiAbstract
In face-to-face, real-time communication, a talking agent must track the target speaker through natural pauses, turn-taking, and backchannels, often amid background cross-talk. Most target speaker extraction (TSE) studies, however, rely on simulated mixtures with full or sparse overlap and ignore the turn-taking of real conversations. We therefore introduce, to our knowledge, the first benchmark for online audio-visual TSE (AV-TSE), built from intact dyadic interactions with independent third-party interference. Observing that anticipating upcoming activity from semantic, acoustic, and facial cues benefits online AV-TSE, we propose an LLM-based target-speaker voice activity projection (TS-VAP) module. Unlike conventional VAP with separated speaker channels, it forecasts the future activity of the target and conversational partner directly from the overlapping mixture, drawing on the linguistic and conversational knowledge of a speech-LLM, and uses this prediction to guide a low-latency separator. We further combine this predictive context with historical and synchronous speaker context. Experiments show that TS-VAP consistently improves streaming extraction across multiple AV-TSE backbones, and that further combining historical, synchronous, and predictive context yields nearly 1 dB gain on real AV conversations. Project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30774
PDF
-
Learning Natural Conversational Behavior in Tandem Speech-to-Speech Models with Randomized Guidance
2026-09-25 03:55:18Manato Yaguchi, Yotaro Kubo, Hikaru Asano, So KurokiAbstract
Tandem speech-to-speech architectures couple a responsive speech frontend with an asynchronous text backend. In KAME, a large language model (LLM) serves as the backend, supplying candidate responses as guidance to the speech frontend while the user is still speaking. Ordinary conversation recordings capture the eventual response but not the guidance the backend would supply during the user's utterance. Generating the missing guidance with a simulator LLM adds substantial data-preparation overhead when training on real conversations. We propose randomized intermediate guidance, which derives guidance directly from the conversation corpus rather than simulating backend LLM behavior. During training, target responses provide informative guidance, while randomly sampled responses provide potentially irrelevant updates during the utterance. This combination aims to teach the frontend to use backend information selectively. On synthetic dialogues, KAME trained with this recipe achieves response quality comparable to that of the LLM-generated and similarity-based baselines. Training on 3.8k hours of real conversations improves smooth turn-taking and audio-judge naturalness over synthetic-data KAME while retaining a response-quality advantage over Moshi. These results show that randomized guidance offers a practical route to combining the response-quality benefits of tandem models with natural conversational behavior learned from real speech.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30773
PDF
-
Training-Free Contextual ASR via SpeechLLM-Based Error-Aware Selective Retrieval
2026-09-25 02:00:44Natsuo Yamashita, Ai Nemoto, Ryosuke Koichi, Masaaki YamamotoAbstract
Recognition of domain-specific and low-frequency terms remains challenging for automatic speech recognition (ASR). Although contextual biasing can improve their recognition, directly providing a large terminology dictionary introduces many irrelevant biasing terms. Retrieval-based contextual biasing addresses this issue by selecting candidate terms from an external dictionary, but querying many recognized words requires numerous dictionary lookups and may yield poorly targeted candidates. We propose a training-free contextual ASR framework in which a pretrained speech large language model (SpeechLLM) jointly generates an ASR hypothesis and localizes error spans likely to involve domain-specific terms. Only the localized spans are used to retrieve phonologically similar terms from an external terminology dictionary. The same SpeechLLM then re-recognizes the audio conditioned on the first-pass hypothesis and the retrieved terms, without task-specific model training. To assess applicability across domains, we evaluate the framework on medical, air traffic control, and financial speech. The proposed method substantially reduces dictionary queries while improving the recall and ranking of relevant terminology candidates and second-pass ASR performance across all three domains.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30694
PDF
-
Adapting Personalized Speech Enhancement for Low-Latency Audio-Visual Target-Speaker Extraction
2026-09-24 23:36:16Rayhan Rashed, Senja Filipi, Ross CutlerAbstract
Online audio-visual target-speaker extraction aims to remove competing voices while preserving speech quality and bounding lookahead. Existing extractors are built and evaluated for separation on synthetic mixtures, leaving listening quality and meeting behavior largely untested. We introduce Audio-Visual Personalized Voice Quality Enhancement (AV-PVQE), which approaches these requirements from the other direction. We start from a personalized speech enhancement model that reconstructs a requested voice at high quality but confuses the target in 46% of two-speaker mixtures despite clean enrollment. Adding mouth features at its speaker-conditioning input and jointly fine-tuning the visual and reconstruction networks reduces this rate to 1.6%, with no future frames and 20 ms of algorithmic delay. Compared with an online autoregressive audio-visual extractor, AV-PVQE yields separation gains on two synthetic benchmarks and larger gains on recorded meetings, and keeps its advantage on excerpts with more speakers than the fine-tuning mixtures. In personalized P.835 listening tests on two meeting corpora, it improves overall quality over this extractor by 0.57 and 0.63 MOS, with similar mean rating relative to the starting model. Preservation and rejection tests show that it keeps the target intact when no competing voice is present and suppresses competing speech when the target is absent.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30631
PDF
-
Audio LLMs Know When They Can't Hear You
2026-09-24 23:22:40Amirhosein Javadi, Richa Dixit, Mehrdad Farajtabar, Minsik Cho, Devang Naik, Mohammad SamraghAbstract
Audio large language models allow users to interact with the model through speech. When an input recording is too degraded, the model may misinterpret the user's query and respond based on an incorrect transcription. In this paper, we study model-conditional transcription reliability: whether an Audio LLM can recognize when its own transcription is unreliable. We first prompt the Audio LLM to assess whether its own transcription would be reliable, and find that the model is a poor judge of its own transcription reliability: in most cases, it predicts that its transcription will be reliable. We find that existing approaches, including speech quality predictors, audio LLM generation uncertainty, and transcript-conditioned WER estimation, provide limited signals for detecting transcription failures. In contrast, we discover that transcription reliability is strongly represented in the model's audio-encoder representations. Based on this observation, we devise a lightweight reliability predictor that operates on representations extracted by the frozen audio encoder and predicts the reliability class before generation. The reliability predictor can trigger a clarification request from the user when their voice query is predicted to be unreliable, while allowing reliable queries to proceed without modifying the underlying Audio LLM. Our predictor achieves 81.10% in-domain and 78.09% cross-domain macro-F1 scores, outperforming the strongest baselines by 10.33 and 11.93 points, respectively. Finally, we show that reliability labels can transfer across Audio LLM families, and that transfer performance is closely related to the alignment of their model-specific reliability boundaries.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30625
PDF
-
Asymmetric Classifier-Free Guidance for Target-Speaker ASR
2026-09-24 19:16:16Yiwen Guan, Jacob WhitehillAbstract
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 inference-time calibration of speaker conditioning. We introduce asymmetric classifier-free guidance (CFG) for TS-ASR using Whisper: the speaker-conditioned branch predicts the target transcript, while the speaker-unconditioned branch predicts serialized multi-speaker transcripts. CFG adjusts the contribution of speaker conditioning during decoding through a single guidance scale. We select a global guidance scale on target-domain development data and train a lightweight encoder-based predictor to adjust it for each utterance, keeping the recognition model fixed. Under domain shifts, our full system achieves relative word error rate (WER) reductions of up to 21.8% over the condition-only baseline, and 5.6% over standard conditional decoding of the same CFG-trained model. Oracle analysis shows that substantially larger WER reductions are possible through utterance-level scale selection and identifies how beneficial adjustments vary with domain shifts.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30476
PDF
-
Inference-Time Target Speaker Unlearning in LLM-Based Automatic Speech Recognition
2026-09-24 18:33:58Bo Su, Yueru Yan, Thai LeAbstract
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 requires an ASR system to transcribe all speakers except the opt-out ones, while still indicating when those speakers are active. As a first step towards tackling this task, we introduce a novel, light-weight Enrollment-Conditioned Gating (ECG) module attachable to a frozen dual-stream speech LLM that enables ASR for new opt-out speakers dynamically during inference, even those who were not seen during initial ECG training phase. Our experiments on both AMI (English) and AliMeeting (Mandarin) datasets show that speech transcription accuracy for corresponding opt-out words or characters falls from 72.3% to 48.2% and from 73.6% to 27.3%, respectively, while retained speakers' transcription error rates maintain more or less the same. Our approach provides a practical solution for modern video conferencing platforms, allowing speakers to dynamically opt-out from automated AI transcriptions without forcefully leaving the meeting sessions, enabling a privacy-preserving interface for potentially millions of online meetings daily.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30439
PDF
-
All In Good Time: Causality-Aware Framework for LLM-Based Simultaneous Speech-to-Speech Translation
2026-09-24 18:13:26Amir Hussein, Enas Albasiri, Travis M. Bartley, Nourchene Ferchichi, Ke Hu, Harishchandra Dubey, Myungjong Kim, Zhehuai Chen, Oluwatobi Olabiyi, Sanjeev KhudanpurAbstract
Large Language Models (LLMs) have shown strong performance in low-resource offline translation; however, extending them to simultaneous speech-to-speech translation (Simul-S2ST) remains challenging due to the scarcity of causally aligned training data with high cross-lingual speaker fidelity. In addition, existing approaches rely on fixed translation policy or confidence heuristics, leading to suboptimal quality and higher latency. We propose a causality-aware Simul-S2ST framework with a novel data pipeline that generates high-fidelity, causally aligned segments with improved voice transfer. The framework introduces (i) a factorized S2ST architecture (FAST), (ii) a causality-aware adaptive policy (CAP), and (iii) causality-aware latency metric. Experiments on CVSS Spanish, German, and French show that FAST-CAP consistently improves the quality-latency trade-off, achieving up to +1.2 BLEU and a 26% relative latency reduction over a fixed policy. Despite using substantially less training data than existing systems, FAST-CAP achieves state-of-the-art results in speech translation quality and speaker fidelity while yielding up to a 38.8% relative reduction in latency.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30416
PDF
-
CLEAR: Online Speech Content Leakage Estimation through Cross-ASR Disagreement
2026-09-24 18:12:38Bhawana Chhaglani, Tanvi Kandepuneni, Jeremy Gummeson, Prashant ShenoyAbstract
Signal-level speech privacy mechanisms suppress linguistic content while preserving acoustic information needed by downstream sensing applications. However, their privacy settings are typically evaluated/selected offline and remain fixed during deployment, even though speech-content leakage can vary substantially across utterances and speakers. Adapting privacy protection at runtime requires estimating how much speech remains recoverable, but conventional measures such as WER or PER require ground-truth transcripts and therefore cannot be computed online. We present CLEAR, a reference-free approach for estimating speech-content leakage at runtime using disagreement among heterogeneous ASR systems. Our key insight is that independently trained ASRs exhibit consistent behavior when linguistic content remains recoverable and increasingly disagree as privacy transformations obscure speech. Using configurable speech-suppression mechanism, we show that cross-ASR disagreement closely tracks transcript-grounded leakage across privacy operating points, achieving a correlation of 0.8. We further characterize the latency-accuracy trade-off of heterogeneous ASR subsets and use their hypotheses to identify potentially exposed words. These capabilities enable privacy to be treated as a runtime property rather than a fixed configuration: CLEAR can communicate residual speech exposure to users and provide feedback for dynamically adjusting privacy aggressiveness while retaining acoustic utility for downstream sensing tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30415
PDF
-
To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech
2026-09-24 17:50:40Debajyoti Mazumder, Mamta, Abhirama Subramanyam PenamakuriAbstract
Online misinformation increasingly appears in spoken formats such as news clips, podcasts, interviews, political speeches, and social media videos, creating a need for fact-checking systems that can verify claims directly from speech. We introduce VeriSpeak, a probe benchmark for studying speech-based fact verification in Large Audio Language Models (LALMs). VeriSpeak contains 3,879 spoken claims spanning temporal, geographical, and relational facts, with balanced true and false labels. The benchmark is designed to examine whether factual verification ability transfers from text to speech, and whether retrieval-augmented LALMs can use textual evidence to correctly support or refute spoken claims. Our experiments reveal a consistent text-speech modality gap: LALMs that verify written claims reliably often fail on the same claims when spoken. Moreover, retrieval alone provides limited gains because models frequently conflate retrieved evidence with the spoken claim. In contrast, retrieval combined with explicit reasoning improves claim-evidence comparison, with a thinking-tuned LALM reaching 86.1% accuracy. VeriSpeak highlights that effective speech misinformation detection requires not only speech understanding, but also grounded reasoning over retrieved evidence. The dataset is publicly available via Hugging Face at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30227
PDF
-
Do Audio Language Models Hear and Read Distinctive Features Alike?
Abstract
Audio language models pass speech and text through a single decoder. We ask whether that decoder represents a distinctive feature in the same direction when a phoneme is heard and when it is read. For minimal pairs of phonemes differing in one feature, we take the offset between the two members' mean representations. Averaging those offsets gives a direction for each stream, and we measure the cosine between the two. Because the two streams already agree about arbitrary phoneme pairs, we compare every measure against a reference built from random pairings rather than against zero. We apply this to 6 models, 7 features and 15 languages from 11 families. Only voicing in the two Qwen2.5-Omni models exceeds that reference after correction for multiple testing, and the reference varies by a factor of seven between models. In three of the six models, voicing has one direction in audio across the 14 languages with enough minimal pairs to measure it, and every language pair agrees in two of them. The model family, not the model size, predicts which stream represents a feature.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30167
PDF
-
A Training Criterion with Token-Level Tolerance to Transcription Ambiguity for Automatic Speech Recognition
2026-09-24 17:17:55Saurabh Kumar, Diptiman Mohanta, Prasanta Kumar GhoshAbstract
Automatic speech recognition is typically trained assuming that the reference transcript is the only valid labeling of an utterance, yet even nominally verbatim transcripts contain localized differences in pronunciation, spelling, or lexical realization that the acoustics do not uniquely determine. Omni-temporal Classification (OTC) tolerates such noise by adding wildcard paths to the connectionist temporal classification (CTC) alignment graph, but its word-level arcs are too coarse, since bypassing one unsupported token discards supervision for the whole word. We move wildcard arcs to token granularity so unsupported tokens can be bypassed while the rest of the word stays supervised, and we combine token- and word-level arcs as complementary escape paths. Across 19 languages and three corpora, token-level OTC improves over CTC on all 25 tasks. We also replace epoch-indexed relaxation of the wildcard weights with a predictive-entropy-indexed schedule, which performs comparably while reducing dependence on training length. Combining this schedule with the hybrid graph gives the lowest mean word error rate (WER) on every corpus and a 9.45% average relative WER reduction over CTC. Independent validator transcriptions show that token-level models place significantly more wildcard-bypass probability than CTC on disputed characters, indicating that token-level tolerance targets localized transcript ambiguity.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30160
PDF
