{"total":31,"items":[{"citing_arxiv_id":"2607.05276","ref_index":22,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions","primary_cat":"eess.AS","submitted_at":"2026-07-06T16:21:34+00:00","verdict":"CONDITIONAL","verdict_confidence":"UNKNOWN","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ProPS uses a mixture density network conditioned on SBERT text embeddings to generate Gaussian mixture models over speaker x-vectors from natural language profile descriptions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.01502","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"From Monolingual to Multilingual: Evaluating Mamba for ASR in South African Languages","primary_cat":"cs.CL","submitted_at":"2026-07-01T22:01:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Mamba matches Conformer accuracy for ASR in seven South African languages with lower compute, multilingual training improves results, and language embeddings aid cross-corpus robustness but do not capture typological similarity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.31947","ref_index":31,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LuxEmo: Expressive Text-to-Speech Corpus for Luxembourgish","primary_cat":"cs.CL","submitted_at":"2026-06-30T16:53:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LuxEmo is a new 21-hour conversational expressive speech corpus for Luxembourgish with 4 emotion categories, created via semi-automatic curation from RTL broadcasts and used to benchmark five TTS systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.31112","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"What Counts as an Error? Dual-Reference Benchmarking for Atypical ASR","primary_cat":"cs.CL","submitted_at":"2026-06-30T04:15:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Dual-reference benchmarking on atypical stuttered speech reveals disparities in ASR model performance and rankings between verbatim and intended transcriptions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.21854","ref_index":47,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ESPnet3: Infrastructure for Scalable Speech and Audio Research in the Foundation Model Era","primary_cat":"eess.AS","submitted_at":"2026-06-20T03:21:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"ESPnet3 introduces a new modular architecture with DataOrganizer and sharding to cut training time and simplify model integration for speech research.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.21305","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LISE : Listenable Interpretable Speaker Embeddings","primary_cat":"cs.SD","submitted_at":"2026-06-19T10:37:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"LISE decomposes pretrained speaker embeddings into components that preserve ASV performance with negligible EER degradation and enable listeners to distinguish speakers at 83.9% accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.18466","ref_index":50,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Montreal Forced Aligner and the state of speech-to-text alignment in 2026","primary_cat":"cs.CL","submitted_at":"2026-06-16T20:18:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"MFA version 3.0 reaches state-of-the-art or near state-of-the-art results on forced alignment benchmarks for English, Japanese, and Korean with average boundary errors under 15 milliseconds.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.17339","ref_index":115,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SpeechDx: A Multi-Task Benchmark for Clinical Speech AI","primary_cat":"cs.AI","submitted_at":"2026-06-15T22:38:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"SpeechDx is a multi-task benchmark with 12 datasets and 27 tasks across health conditions, structured by conceptualization, formulation, and articulation stages, showing that no current audio encoder generalizes reliably.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.20680","ref_index":44,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Beyond ROC-AUC: Operating-Point Performance Reporting for Biometric Verification","primary_cat":"cs.CV","submitted_at":"2026-06-13T15:28:54+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Full ROC-AUC can hide or reverse low-FMR performance differences, as FaceNet outperforms ArcFace on AUC but underperforms at FMR=10^-3 with statistical significance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07240","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"KIT's Submission to Cross-Lingual Voice Cloning in IWSLT 2026","primary_cat":"cs.CL","submitted_at":"2026-06-05T13:09:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"KIT's IWSLT 2026 submission adapts a multilingual TTS model with language prompting, RL fine-tuning, and reference-conditioned lexical matching, reporting largest gains from prompting.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.01135","ref_index":34,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Spiking and Event-driven Neuromorphic Mamba Models for Efficient Speech Recognition","primary_cat":"cs.NE","submitted_at":"2026-05-31T10:15:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Event-driven SpeechMamba with FATReLU reaches over 60% sparsity and spiking version over 70% sparsity with <1% accuracy drop while cutting parameters 30% versus prior SNNs, plus a new cycle-accurate simulator.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.27874","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Syllabic-Structure Decoder for Automatic Speech Recognition in Vietnamese","primary_cat":"cs.CL","submitted_at":"2026-05-27T02:51:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A phoneme-based syllabic decoder for Vietnamese ASR outperforms larger-vocabulary baselines like PhoWhisper on standard and multi-dialect benchmarks while using a compact inventory.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.26978","ref_index":19,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PashtoTTS-Bench: automated screening for low-resource non-Latin-script text-to-speech","primary_cat":"cs.CL","submitted_at":"2026-05-26T13:03:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Introduces INSV-A automated screening benchmark for Pashto TTS systems reporting WER, script fidelity, and LID results across five systems on FLEURS and Common Voice prompts.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.24451","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Phonetic Modeling of Dialectal Variation in Vietnamese Speech","primary_cat":"cs.CL","submitted_at":"2026-05-23T08:00:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Dialect-specific phonetic vocabulary and joint decoder for Vietnamese ASR that matches wav2vec2-base-vi-250h performance with fewer parameters and no pretraining on the UIT-ViMD dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20299","ref_index":43,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Mechanisms of Misgeneralization in Physical Sequence Modeling","primary_cat":"cs.LG","submitted_at":"2026-05-19T12:34:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Generative sequence models for physical tasks exhibit physical misgeneralization where local prediction errors propagate through physical measurements to distort aggregate distributions over quantities like distance or energy; a data deviation kernel explains and predicts the shifts and supports a内核","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07291","ref_index":34,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Evaluating voice anonymisation using similarity rank disclosure","primary_cat":"eess.AS","submitted_at":"2026-05-08T06:01:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SRD provides a threshold-independent, representation-level privacy assessment for voice anonymization that reveals system weaknesses not detected by equal error rate evaluation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.03671","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Paradigm for Interpreting Metrics and Identifying Critical Errors in Automatic Speech Recognition","primary_cat":"cs.CL","submitted_at":"2026-05-05T12:09:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A paradigm converts any metric into a minimum edit distance equivalent to interpret ASR errors in terms of human perception and severity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.27542","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HATS: An Open data set Integrating Human Perception Applied to the Evaluation of Automatic Speech Recognition Metrics","primary_cat":"cs.CL","submitted_at":"2026-04-30T07:48:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"HATS supplies human side-by-side preference judgments on ASR transcripts to measure correlation with lexical and embedding-based evaluation metrics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.26676","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Toolkit for Detecting Spurious Correlations in Speech Datasets","primary_cat":"cs.SD","submitted_at":"2026-04-29T13:47:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A toolkit flags spurious correlations in speech datasets by checking if non-speech regions predict the target class better than chance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.20229","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Enhancing Speaker Verification with Whispered Speech via Post-Processing","primary_cat":"cs.SD","submitted_at":"2026-04-22T06:23:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Post-processing with an encoder-decoder model yields 22% relative EER reduction on normal-vs-whispered trials and 1.88% EER on whispered-vs-whispered, outperforming ReDimNet-B2.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19330","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Text-To-Speech with Chain-of-Details: modeling temporal dynamics in speech generation","primary_cat":"eess.AS","submitted_at":"2026-04-21T10:58:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Chain-of-Details (CoD) is a cascaded TTS method that explicitly models temporal coarse-to-fine dynamics with a shared decoder, achieving competitive performance using significantly fewer parameters.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19151","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Voice of India: A Large-Scale Benchmark for Real-World Speech Recognition in India","primary_cat":"cs.CL","submitted_at":"2026-04-21T07:02:01+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19028","ref_index":224,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors","primary_cat":"cs.LG","submitted_at":"2026-04-21T03:23:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"NodePFN pre-trains on synthetic graphs with controllable homophily and causal feature-label models to achieve 71.27 average accuracy on 23 node classification benchmarks without graph-specific training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.15923","ref_index":44,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Hierarchical Codec Diffusion for Video-to-Speech Generation","primary_cat":"cs.SD","submitted_at":"2026-04-17T10:28:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"HiCoDiT generates speech from video by conditioning low-level RVQ tokens on speaker identity and high-level tokens on facial expressions via a dual-scale normalized diffusion transformer.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.13335","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SEDTalker: Emotion-Aware 3D Facial Animation Using Frame-Level Speech Emotion Diarization","primary_cat":"cs.CV","submitted_at":"2026-04-14T22:55:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"SEDTalker uses frame-level speech emotion diarization to condition a hybrid Transformer-Mamba model for fine-grained, temporally continuous emotion control in 3D facial animation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.12398","ref_index":58,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Contextual Biasing for ASR in Speech LLM with Common Word Cues and Bias Word Position Prediction","primary_cat":"eess.AS","submitted_at":"2026-04-14T07:33:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Common-word acoustic cues and bias-word position prediction in speech LLMs cut rare-word transcription errors by 16.3% versus baselines, including out-of-domain cases.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08450","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DeepFense: A Unified, Modular, and Extensible Framework for Robust Deepfake Audio Detection","primary_cat":"cs.SD","submitted_at":"2026-04-09T16:47:18+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":5.0,"formal_verification":"none","one_line_summary":"DeepFense supplies a unified toolkit and large-scale benchmarks showing that pre-trained front-end feature extractors drive most performance differences while top models exhibit strong biases by audio quality, speaker gender, and language.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.20896","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Study of Data Selection Strategies for Pre-training Self-Supervised Speech Models","primary_cat":"cs.SD","submitted_at":"2026-01-28T08:56:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Prioritizing longest utterances in SSL speech pre-training data outperforms random or diversity-based sampling for ASR performance while using half the data volume.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.10785","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FAC-FACodec: Controllable Zero-Shot Foreign Accent Conversion with Factorized Speech Codec","primary_cat":"cs.SD","submitted_at":"2025-10-12T20:02:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FAC-FACodec is a controllable zero-shot foreign accent conversion framework using a factorized speech codec that adds an explicit parameter for adjusting pronunciation-level accent modification strength.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.23511","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks","primary_cat":"eess.AS","submitted_at":"2025-07-31T12:47:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"MECAT is a multi-expert benchmark for audio AI offering fine-grained captions and QA pairs generated via expert models and LLM reasoning, paired with the DATE metric that combines semantic similarity and cross-sample discriminability to favor detailed outputs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2406.14294","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DASB - Discrete Audio and Speech Benchmark","primary_cat":"cs.SD","submitted_at":"2024-06-20T13:23:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"DASB is a new benchmark for discrete audio tokens showing semantic tokens outperform acoustic ones but discrete representations remain less robust than continuous features across domains.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}