Speech Processing

Follow this topic Ask about this topic

Momentum

48 papers in the last four weeks, up 433% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 295

Jun 15, 2026eess.AS

Decoding while Adapting: Zero-Shot Online Speaker Adaptation via Audio-Textual Prompts for Elderly Speech Recognition

This paper proposes a novel cross-utterance audio-textual prompts based speaker adaptation approach for elderly speech recognition. It enables zero-shot, real-time adaptation to unseen speakers. Speech and text embeddings are extracted from the current and a few preceding utterances, before being fused in a cross-modal manner to produce compact speaker prompts that are more consistent than i/x-vectors and ECAPA-TDNN features. Experiments on the English DementiaBank Pitt and Cantonese JCCOCC MoCA elderly speech datasets suggest that the proposed online adaptation outperforms the speaker-independent (SI) model by statistically significant word error rate (WER) or character error rate (CER) reductions of 0.61% and 1.22% absolute (2.99% and 4.48% relative). Real-time factor (RTF) speed-up ratios of up to 9.83 times are obtained over offline batch-mode adaptation.

Chengxi Deng, Xurong Xie, Shujie Hu +7

The Chinese University of Hong Kong, Hong Kong SAR, China · Institute of Software, Chinese Academy of Sciences, China · National Research Council Canada, Canada

Speech Processing Automatic Speech Recognition

Jun 15, 2026cs.CL

TMASC: Transmasculine Attitude and Speech Corpus

We introduce the Transmasculine Attitudes and Speech Corpus (TMASC), a multimodal corpus of 196 transmasculine individuals, including questionnaire responses and 66 audio recordings. The questionnaire includes items exploring the vocal health of transmasculine individuals. The audio recordings include cough and throat-clearing samples, a reading passage, and additional session-specific questions. This paper outlines the development of this corpus and the data collection procedures. To illustrate the utility of this corpus, we present three case studies demonstrating how this crowd-sourced multimodal corpus can be used to support transmasculine individuals. These include the integration of perceptual and acoustic data, the identification of group-level characteristics, and the calibration of acoustic measurements.

Sidney Wong

Centre for Sustainability Research, University of Otago, New Zealand · Te P¯unaha Matatini Centre of Research Excellence for Complex Systems, New Zealand

Speech Processing

Jun 15, 2026cs.SD

ArtBoost: Synthetic Articulatory Data Augmentation for Acoustic-to-Articulatory Inversion

Recent acoustic-to-articulatory inversion (AAI) models rely on electromagnetic articulography (EMA) data, which are costly and limited in scale. To address this limitation, we propose \textit{ArtBoost}, a novel data augmentation strategy that leverages large-scale speech--mesh datasets originally developed for speech-driven 3D facial animation to improve AAI under limited EMA supervision. \textit{ArtBoost} extracts pseudo articulatory trajectories from visible facial anchors and uses them for pre-training before fine-tuning on real EMA data. Experiments show consistent improvements in PCC and RMSE. Trajectory analyses confirm that the pseudo articulatory signals reflect physically meaningful visible articulatory dynamics. Additional evaluations across different AAI architectures demonstrate stable performance gains, indicating that \textit{ArtBoost} can be integrated into diverse AAI models. These results suggest that speech--mesh data provide an effective and scalable source of articulatory supervision for AAI. Project page: https://cau-irislab.github.io/Interspeech26-ArtBoost/

Hyung Kyu Kim, Byungchan Hwang, Hak Gu Kim

Department of Imaging Science and Arts, Chung-Ang University, South Korea · Department of Metaverse Convergence, Chung-Ang University, South Korea

Synthetic Data Augmentation Data Augmentation Speech Processing

Jun 15, 2026eess.AS

Stabilizing Short Duration Speaker Verification through Neural Re-scoring with Hybrid Enrollment

Short-duration speaker verification (SDSV) is crucial for personalized keyword spotting, where test utterances are typically shorter than three seconds. Limited speech duration results in unstable speaker representations and increased sensitivity to noise and phoneme variations, thereby degrading performance. To investigate this issue, we construct VoxPhrase, a large-scale SDSV corpus automatically segmented from the VoxCeleb dataset. Our analysis shows that text-dependent (TD) enrollment is constrained by duration and yields unstable speaker representations. In contrast, although text-independent (TI) enrollment introduces content mismatch, its representations become more stable as the enrollment duration increases. Accordingly, we propose a hybrid-enrollment neural re-scoring framework that combines TD and TI enrollment and performs frame-level comparison via parallel cross-attention. Experiments on VoxPhrase demonstrate consistent improvements across multiple speaker models.

Zhiqi Ai, Han Cheng, Shiyi Mu +3

Shanghai University, China · Hithink RoyalFlush AI Research Institute, China · Xi’an Jiaotong-Liverpool University, China

Speaker Verification Speech Processing

Jun 14, 2026cs.CL

Scaling Human and G2P Supervision for Robust Phonetic Transcription

Expert phonetic annotation is costly, especially for non-standard dialects and atypical speech. A common alternative is using Grapheme-to-Phoneme (G2P) models to auto-generate phonetic labels from text transcripts at scale. We study how automatic phonetic transcription performance scales with human and G2P supervision in English. Using a curated 80-hour benchmark spanning native, non-native and post-stroke speech, we identify a supervision quality threshold: G2P supervision helps only when fewer than 20-30 hours of human annotation are available. Beyond this threshold, it provides no significant benefit and can reduce cross-dialect robustness. What is effective after this threshold is ASR pretraining which we use to achieve a 2.3x reduction in weighted phone feature error rate over prior systems, with strong gains on non-native and aphasic speech. These results suggest that quantity-driven G2P scaling may yield diminishing returns for robust generalization.

Alexander Metzger, Aruna Srivastava, Ruslan Mukhamedvaleev

Koel Labs LLC, USA

Speech Processing Automatic Speech Recognition G2P Conversion

Jun 14, 2026eess.AS

MambAdapter: Lightweight Mamba-Based Adapters for Parameter-Efficient Transfer Learning in Speech and Audio

Fine-tuning Transformer-based foundation models has become the dominant strategy for domain adaptation in audio and speech processing. To reduce the computational and memory costs of this process, parameter-efficient transfer learning (PETL) methods have been widely explored. Meanwhile, Mamba, a recent state-space model, has emerged as a promising alternative to Transformers for sequence modeling. In this work, we present MambAdapter, a parameter-efficient transfer learning approach that integrates Mamba into low-rank bottleneck adapters. Our design combines parameter sharing across adapters with the injection of a lightweight Mamba module, enabling more effective modeling of audio features. We demonstrate that MambAdapter matches or outperforms strong PETL baselines on four audio classification tasks and five speech recognition languages, even when operating under reduced parameter budgets.

Salman Hussain Ali, Umberto Cappellazzo, Mirco Ravanelli

1Universit´e de Montr´eal, Canada · 2Imperial College London, UK · 3Concordia University, Canada +1

Mamba Speech Processing Audio Classification Parameter-Efficient Fine-Tuning

Jun 14, 2026cs.SD

AP-GRPO: Anchor-Gated Phonetic Alignment with Policy Optimization for Pathological Speech Reconstruction

Pathological speech from patients with neurodegenerative and neuromotor disorders is often acoustically distorted and linguistically fragmented, making pathological speech reconstruction necessary to recover intended textual content from distorted and incomplete speech recordings. Crucially, such recordings are rarely uniformly degraded: some words or short phrases remain reliable and can serve as audible anchors for reconstructing the corrupted surrounding content. We introduce Anchor-gated Phonetic Group Relative Policy Optimization (AP-GRPO), a GRPO framework with phonetic reward that aligns speech language models (SLMs) through audible-anchor preservation and inter-anchor phonetic compatibility to the original speech signal. AP-GRPO consists of: (i) an anchor-gated reward that matches reliable audible anchors in clear regions; and (ii) an inter-anchor phonetic alignment reward that evaluates whether recovered contents are phonetically supported by the corresponding corrupted inter-anchor speech span. Across four disease conditions, AP-GRPO improves faithful speech reconstruction, and the learned anchor constraint automatically adapts to each condition and thus reveals interpretable disease-specific profiles: conditions with severe articulatory degradation require stronger anchor enforcement, whereas milder impairment or linguistically impaired conditions rely more on phonetic alignment for inter-anchor recovery.

Pengfei Zhang, Hoang H Nguyen, Yutong Song +6

University of California Irvine · University of Illinois Chicago · Kennesaw State University

RL for Language Models Speech Processing Speech Language Models

Jun 13, 2026cs.CL

Prior over Evidence: Stereotype-Driven Diagnosis in LLM-Based L2 Pronunciation Feedback

Large language models are increasingly deployed for written pronunciation feedback in second-language (L2) English learning, under the assumption that their diagnoses are grounded in the supplied speech evidence rather than in priors from pretraining. This assumption is tested on 1,800 L2-Arctic utterances spanning six L1 backgrounds, three audio-capable LLMs, four pronunciation dimensions, and five evidence conditions ranging from a text-only baseline to numeric acoustic features and raw audio. Each (utterance x model x condition x dimension) cell is scored on three metrics: Rating Accuracy (RA) against gold labels, Evidence Coherence (EC) assessing internal consistency without ground truth, and Grounded Correctness (GC) evaluated against gold evidence. Results show three findings across models. First, rating accuracy and grounded reasoning decouple: 39.6% of judged cells contain internally coherent reasoning that supports a wrong rating, against only 15.8% where the reasoning supports a correct rating. Second, phoneme-level feedback converges to a fixed inventory of L2-English difficulty phones that recurs across all six L1 backgrounds and all evidence conditions. Third, acoustic evidence improves the rating only when the supplied feature directly probes the target dimension: textualised F0 range raises pitch-variation grounding from (0.18-0.19) to (0.45-0.62) across all three models, while stress and phoneme correctness, which require target-to-realisation alignment, remain ungrounded. The same audio waveform without textualised F0 values does not reproduce this improvement. These findings indicate that current general-purpose LLMs are more reliable as verbalisers of externally computed pronunciation evidence than as standalone diagnostic engines.

Rong Wang, Kun Sun

University of Tuebingen, Tuebingen, Germany · Tongji University, Shanghai, China

Audio-Language Model Evaluation LLM Grounding Speech Processing Language Model Bias Evaluation

Jun 12, 2026cs.CL

Learning to Hear Hesitation: Continual Learning for Disfluency-Aware ASR

Despite advances in large-scale Automatic Speech Recognition (ASR), disfluent speech remains challenging, as state-of-the-art systems are often optimized to omit disfluencies, leading to information loss and hallucinations. Prior work has focused on verbatim transcription and the integration of disfluency markers, but adapting models on limited datasets can lead to catastrophic forgetting of general-domain knowledge. We address this gap by leveraging continual learning (CL) with explicit disfluency tokens. We first introduce these tokens into a pretrained ASR model to establish stable token mechanisms, and then continue training on additional datasets with varying disfluency distributions. Through a detailed analysis of model dynamics during training, we identify a trade-off between marker learning and ASR performance, and a consistent cross-attention head mechanism shared across CL methods.

Henri-Leon Kordt, Theresa Pekarek Rosin, Jae Hee Lee +1

Knowledge Technology, Department of Informatics, University of Hamburg, Germany

Speech Processing Automatic Speech Recognition

Jun 12, 2026cs.SD

MaskedFOP: Polyglot Speaker Identification under Missing Visual Modality via Cascaded Graph Label Propagation

We present MaskedFOP, a system for closed-set polyglot speaker identification under two simultaneous challenges: the face modality is entirely absent at test time, and speech comes from Urdu, a language unseen during face-supervised training. The system integrates three complementary mechanisms. First, a modality-dropout dual-head network built on the Fusion and Orthogonal Projection (FOP) backbone forces the audio branch to develop independent discriminative power via per-sample face masking, ensuring that the audio encoder remains capable when face is absent. Second, two MaskedFOP instances trained on Emphasized Channel Attention, Propagation, and Aggregation in Time Delay Neural Network (ECAPA-TDNN) features with different random seeds produce complementary audio embeddings whose element-wise average yields a more robust 512-dimensional representation than any single model. Third, a two-stage cascaded inference procedure first refines multimodal labels through a fused Graph Label Propagation (GLP) pass (Stage 1), then assigns audio-only labels by cosine nearest-centroid (Stage 2), replacing the 70 sparse training prototypes with ~1,500 in-domain test-set centroids from Stage 1. Submitted to the POLY-SIM 2026 Grand Challenge, the system achieves a mean P-accuracy of 0.9989, placing first among all submissions evaluated on the challenge server. An ablation identifies cascaded seeding as the single largest gain (>8 pp on P4/P6). The code is available at https://github.com/Ayoub-Elkhouzari/POLY-SIM2026.

Ayoub Elkhouzari, Youssef Iraqi, Loubna Mekouar

College of Computing, University Mohammed VI Polytechnic

Missing-Modality Learning Speech Processing

Jun 11, 2026cs.LG

Predicting Cognitive Load from Speech and Interaction Dynamics in Dyadic Conversations

Estimating cognitive load from speech has largely been studied in controlled laboratory settings, with limited understanding of its reliability in natural collaborative conversations. We investigate whether speech and interaction dynamics predict perceived cognitive load during dyadic conversations. We analyze audio from 53 dyads performing nine collaborative tasks and extract static acoustic, dynamic, and interaction features to train a two-head Gated Recurrent Unit encoder to predict cognitive load scores. Results show conversational interaction provides useful signals for predicting cognitive load related to time pressure, mental work, effort, and task performance. Temporal demand is associated with turn-taking dynamics such as overlap and speaker switch, while mental demand is linked to imbalanced participation between speakers. These findings highlight the importance of task structure and conversational interaction for modeling cognitive load in natural collaborative settings.

Tahiya Chowdhury

Department of Computer Science, Colby College, Waterville, Maine, USA

Speech Processing

Jun 10, 2026cs.SD

Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering

This paper presents a novel data-free and training-free compression approach for speech foundation models using channelwise clustering via k-means. More fine-grained, mixed sparsity pruning by layer-level varying number of parameter clusters is also explored. Experiments conducted on the LibriSpeech dataset suggest that when operating with pruning sparsity of 50% on HuBERT-large, consistent WER reductions of 27.73%/18.61% absolute (34.37%/21.91% relative) over the magnitude-based pruning were obtained on the test-clean and test-other subsets before fine-tuning and 0.19%/0.79% absolute (3.36%/4.62% relative) after fine-tuning with only 3 epochs. Similar WER reductions of 2.86%/5.02% absolute (59.21%/55.29% relative) were observed against magnitudebased pruning on Whisper-large-v3 at 10% sparsity, all with no significant WER increase relative to the uncompressed baseline.

Haoning Xu, Zhaoqing Li, Huimeng Wang +4

The Chinese University of Hong Kong, Hong Kong SAR, China · National Research Council Canada, Canada

Speech Foundation Models Clustering Speech Processing Neural Network Compression Neural Network Pruning

Jun 10, 2026eess.AS

Tight Boundary Prediction in Speaker Diarization Using Causal-Anticausal Consistency

Multi-talker conversational automatic speech recognition data are often used to train speaker diarization models. Because such data prioritize semantic continuity, pauses and boundary margins are included within speech segments, resulting in loose annotations. Models trained on such data tend to internalize mechanisms that reproduce this looseness, although tight speech intervals are sometimes preferable for downstream applications. In this paper, we address the novel task of enabling models to produce tight predictions using loose labels. Our method generates tighter pseudo labels using causal and anticausal models, which are inherently incapable of learning loosening behavior. We further propose a co-training scheme that iteratively tightens labels and updates both models for more progressive refinement. Experimental results show that the proposed method recovers about 70 % of the tightening effect achieved by ideal tight-label training and improves downstream performance.

Shota Horiguchi, Marc Delcroix, Naohiro Tawara +2

NTT, Inc., Japan

Speech Processing Learning with Noisy Labels Speaker Diarization

Jun 10, 2026eess.AS

Fast Speech Foundation Model Distillation Using Interleaved Stacking

Distilling a large speech foundation model (SFM) into an efficient student model has been successfully applied to low-resource environments. Although distillation reduces inference latency, it requires an additional student model training. However, the training efficiency of SFM distillation remains underexplored. In this work, we explore training acceleration of SFM distillation to speed up model deployment. We examine the potential of stacking, in which the model depth is progressively increased through training until the target model depth is reached. While existing stacking methods improve training speed, they suffer from performance degradation. To handle this limitation, we propose interleaved stacking, a novel stacking method that consistently preserves layer position throughout the stacking process. This property is particularly critical in SFMs, in which each layer encodes distinct layer-specific knowledge. We validate the effectiveness of the proposed method on SUPERB.

Eungbeom Kim, Kyogu Lee

1IPAI, 2AIIS, 3Dept. of Intelligence and Information Seoul National University, Seoul, Republic of Korea

Speech Foundation Models Speech Processing Speech Language Models Knowledge Distillation

Jun 10, 2026eess.AS

Benchmarking Neural Speech Compression from a Rate-Distortion Perspective

Learning-based speech compression has achieved promising low-bitrate performance, but many neural speech codecs still describe quantized latents with preset-rate discrete symbols or apply entropy coding only after symbol generation. Such designs decouple representation learning from probability modeling, limiting their ability to exploit the non-uniform usage and temporal dependencies of learned speech latents. In this paper, we benchmark neural speech compression from a rate--distortion perspective and further investigate entropy-constrained coding for low-bitrate speech compression. We first formulate a unified learning-based speech coding pipeline and provide a benchmark-style analysis of recent neural speech codecs, showing that explicit probability modeling remains underexplored in learned speech compression. We then propose ECC, an Entropy-Constrained Codec that combines scalar quantization with a learned entropy model. ECC integrates hyperprior-based side information, channel-wise context modeling, latent residual prediction, and lightweight temporal modeling to estimate latent likelihoods for rate estimation during training and arithmetic coding during inference. To further improve low-bitrate efficiency, ECC introduces entropy skip, which omits highly predictable residual symbols using decoder-available scale estimates without transmitting additional skip masks. Extensive experiments show that ECC achieves a favorable low-bitrate rate--distortion trade-off over conventional and neural codec baselines, reducing BD-rate by 39.9% on ViSQOL and 76.3% on PESQ on average over two widely-used test sets. Ablation and diagnostic studies further validate the effectiveness of entropy modeling. Project Page: https://avery-xu.github.io/ECC-demo/

Jun Xu, Zhengxue Cheng, Fengxi Zhang +3

School of Information Science and Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China

Neural Audio Codecs Speech Processing Rate-Distortion Optimization Entropy Coding

Jun 10, 2026cs.SD

SARA: A Dual-Stream VAE for High-Fidelity Speech Generation via Integrating Semantic and Acoustic Representations

Zero-shot text-to-speech (TTS) relies on robust speech representations. However, current speech tokenizers face a fundamental trade-off: acoustic codecs preserve high-fidelity audio but lack linguistic constraints, causing content errors during generation, whereas semantic tokens from self-supervised learning (SSL) models ensure precise text alignment but discard some acoustic information. To bridge this gap, we propose SARA, a dual-stream VAE that directly fuses a frozen SSL semantic anchor with a dedicated residual acoustic encoder. This effectively mitigates the dilemma, creating an efficient and compact latent space without relying on complex regularizers. SARA achieves superior reconstruction quality over strong baselines. Furthermore, in downstream zero-shot TTS tasks, it yields highly natural and expressive synthesis quality, and maintains robust generation performance even under accelerated inference, offering a favorable trade-off between synthesis speed and computational cost.

Peijie Chen, Wenhao Guan, Weijie Wu +7

School of Informatics, Xiamen University, China · School of Electronic Science and Engineering, Xiamen University, China · DiDi Global Inc., Beijing, China

Variational Autoencoders Audio Representation Learning Speech Processing Zero-Shot TTS Text-to-Speech

Jun 9, 2026cs.SD

CS-YODAS: A Mined Dataset of In-the-Wild Code-Switched Speech

We present CS-YODAS, a Creative Commons-licensed dataset of in-the-wild code-switched speech mined from multilingual YouTube data. Code-switching (CS), or the alternation between languages within an utterance or conversation, is common in multilingual settings but remains underrepresented in existing CS speech resources, which are typically small, domain-specific, or artificially constructed. Building on the YODAS corpus, we develop a scalable, human-in-the-loop pipeline for identifying and validating naturally occurring code-switching. The resulting dataset, which totals 313 hours and spans 7 matrix languages, provides diverse, real-world examples of spontaneous code-switched speech. We further analyze the distribution and characteristics of code-switching in the wild, examining language-pair frequencies and switching patterns, and report baseline results for spoken language identification. We hope that CS-YODAS will encourage broader and more comprehensive research on code-switched speech. Dataset link: https://huggingface.co/datasets/byan/cs-yodas.

Brian Yan, Qingzheng Wang, Matthew Wiesner +9

Carnegie Mellon University · Johns Hopkins University · University of Texas at Austin +4

Code-Switching Speech Processing

Jun 9, 2026cs.CL

The Dynamics of Human and AI-Generated Language: How Semantics Fluctuates across Different Timescales

Spoken language, whether produced by humans or large language models (LLM), unfolds over time with varying semantic content. However, we still lack simple, interpretable time-series features that capture how generic versus specific content is distributed over time, and that can be used to compare human and AI-generated speech. We introduce a semantic-timescale analysis pipeline that turns word-level transcripts with timestamps into semantic time-series. For each spoken narrative, we compute (i) semantic specificity using WordNet-based word depth and (ii) contextual similarity using SBERT embeddings and quantify their temporal dependence using autocorrelation-window measures (ACW-0 and related metrics). We then compare original speech to multiple shuffled controls that selectively disrupt lexical identity, temporal order, and word duration. Across human-read autobiographical narratives, TTS readings, and LLM-generated texts rendered with TTS, we find that segments with longer ACW-0 in the semantic time-series tend to contain more generic vocabulary, whereas segments with shorter ACW-0 are enriched in more specific words. These associations are strongly attenuated or abolished when word order and timing are randomized, indicating that ACW-based measures capture non-trivial temporal organization of semantic content beyond static lexical distributions. Our results suggest that ACW-based semantic timescales are a useful family of features for analyzing and comparing the temporal structure of human and AI-generated speech.

Han-Jen Chang, Yasir Çatal, Angelika Wolman +5

Speech Processing

Jun 9, 2026cs.SD

ContextCodec: Content-Focused Context Guidance for Ultra-Low Bitrate Speech Coding

Neural speech codecs enable low-bitrate speech communication, yet at ultra-low bitrates (< 1000 bps) preserving perceptual quality and intelligibility is challenging. Existing designs often prioritize acoustic details, leaving limited capacity for the core linguistic message under tight bitrate constraints. To address this, we propose ContextCodec, a codec that transmits content-focused context features to explicitly guide reconstruction. ContextCodec adopts a dual-branch encoder that decouples acoustic details from content-focused context. The context branch is trained with a CLIP-style contrastive loss that aligns context features with phoneme indices, reducing paralinguistic leakage. During decoding, these features are injected at each decoding stage for explicit guidance. In addition, we introduce a lightweight autoregressive latent refinement module. Experiments show a strong quality-intelligibility trade-off down to 500 bps, with an RTF of 0.4886 on a typical mobile CPU.

Chengbin Liang, Wenqi Guo, Hao Cao +1

Department of Electronic Engineering, Tsinghua University, Beijing, China · Department of Automation, Tsinghua University, Beijing, China

Neural Audio Codecs Speech Processing

Jun 9, 2026cs.SD

ViP-VL: Vietnamese Self-supervised Speech Pretraining Model with Vector-Quantization Learning

We present ViP-VL, an efficient Vietnamese Self-supervised speech Pretraining model leveraging Vector-quantization Learning. To bridge the gap between high-resolution audio and efficient processing, ViP-VL incorporates Acoustic Stacking and Receptive Field Alignment to enable a synchronized 8x subsampling rate within the ChunkFormer architecture, while further enhancing representation robustness through a specialized Mask Selection Strategy during pretraining on the BEST-RQ framework. Pretrained on 17,000 hours of unlabeled Vietnamese speech, our model establishes new state-of-the-art results across four major downstream tasks: Automatic Speech Recognition, Speech Emotion Recognition, Dialect Classification, and Speaker Verification. To facilitate future research and the development of high-performance Vietnamese speech technologies, we publicly release our pretrained weights and implementation at github.com/khanld/chunkformer.

Khanh Le, Kiet Anh Hoang, Bao Nguyen +5

VinUniversity, Vietnam · UNEY, Switzerland

Audio Representation Learning Speech Processing Audio Understanding Automatic Speech Recognition Self-Supervised Speech Representation Learning Discrete Speech Representation Learning

Jun 9, 2026eess.AS

SSL-GMMVC: Interpretable Voice Conversion via Locally Linear GMM Transforms in Self-Supervised Representation Space

We introduce SSL-GMMVC, an interpretable voice conversion method in self-supervised speech space. The method models paired source-target features with a Gaussian mixture model and performs conversion as a posterior-weighted sum of affine transforms. This yields locally linear transformations that adapt to heterogeneous feature-space structure while remaining analytically tractable. Through objective and subjective evaluations, we show that SSL-GMMVC improves speaker similarity with comparable intelligibility and naturalness, and that even a constrained covariance variant surpasses a deep learning baseline as the number of mixture components increases. Further analyses link component selection to phonetic structure and reveal interpretable scaling and rotation in the learned transforms. These findings highlight SSL-GMMVC as an effective, analyzable framework for voice conversion.

Tomoya Tanabu, Hiroshi Nishijima, Daisuke Saito +1

The University of Tokyo, Japan

Gaussian Mixture Models Interpretable ML Speech Processing Voice Conversion

Jun 8, 2026cs.SD

Automated Pronunciation Evaluation for Korean Toddler Speech using Speech Diarization and Self-Supervised Learning

Speech sound disorders affect approximately 44% of Korean pediatric communication disorder cases, yet automated assessment tools for Korean toddler speech remain underdeveloped. This paper presents an end-to-end pipeline for automated pronunciation evaluation of Korean toddler speech, combining neural speaker diarization with self-supervised speech representation learning. We introduce a novel IRB-approved corpus of 53 recordings from Korean-speaking children aged 2-5 years. A subset of 53 subjects was annotated by three independent reviewers, yielding 1,190 consonant and 748 vowel word-level binary correctness labels. We evaluate three diarization models, finding that NeMo SortFormer achieves 88.69% speaker count accuracy and 33.04% diarization error rate (DER) owing to its arrival-time-sorted transformer architecture, which handles the acoustic confound between young female caregivers exhibiting aegyo and toddler speech. For pronunciation scoring, we compare three self-supervised learning (SSL) backbones across multiple pooling strategies. A cross-model ensemble routing consonant prediction to HuBERT-large and vowel prediction to WavLM-large achieves balanced accuracies of 0.720 and 0.845, with a mean of 0.782.

Diane Myung-kyung Woodbridge, Jee Hyun Suh

Masters in Data Science and Artificial Intelligence Program University of San Francisco · Department of Rehabilitation Medicine Seoul National University Bundang Hospital

Speech Processing Self-Supervised Speech Representation Learning Speaker Diarization

Jun 8, 2026eess.AS

MeCo: One-Step MeanFlow-based Corrector for Multi-Channel Speech Separation

While discriminative models for multi-channel speech separation excel in reference-based metrics, they often exhibit suboptimal human listening quality. To address this, we propose a novel MeanFlow-based one-step generative corrector (MeCo). MeCo learns a conditional average velocity field to map discriminative estimates directly onto the clean speech manifold in a single step. To maximize one-step generation performance, we introduce Data-Space Optimization (DSO). DSO integrates an

\mathbf{x}_r

-loss, which penalizes prediction errors on longer displacement intervals to serve as a generative objective for human listening quality, with an Endpoint SI-SDR loss that directly optimizes terminal signal fidelity. Experiments demonstrate that MeCo achieves state-of-the-art (SOTA) performance with minimal computational overhead, simultaneously achieving superior signal fidelity and human listening quality in both in-domain and out-of-domain scenarios.

Dohwan Kim, Jung-Woo Choi

School of Electrical Engineering, KAIST, Daejeon, Republic of Korea

Flow Matching MeanFlow Speech Processing One-Step Generative Modeling Audio Source Separation Speech Separation

Jun 8, 2026cs.CL

A Finetuned SpeechLLM for Joint Multi-Granular L2 Assessment and Natural-Language Rationales

Automated L2 speech assessment can assign proficiency labels, but often lacks interpretability. We propose a rubric-guided SpeechLLM for multi-aspect, multi-granular assessment, trained with a hybrid objective combining supervised fine-tuning and Bounded Direct Preference Optimization. The model jointly predicts ordinal labels at the sentence-level (accuracy, fluency, prosody), word/phoneme-level accuracy, and generates a natural-language rationale in the same response. On SpeechOcean762, our approach matches or outperforms single-granularity models while remaining competitive with prior approaches. We analyze rationale reliability along two axes: self-consistency with model predictions and alignment with ground-truth labels, using sentiment consistency (plausibility) and mention-based agreement (faithfulness). Rationales are plausible at the sentence level, but faithfulness degrades at the word/phoneme level: references are sparse and weakly aligned with token-level labels.

Aditya Kamlesh Parikh, Cristian Tejedor-Garcia, Catia Cucchiarini +1

Centre for Language Studies, Radboud University, Nijmegen, The Netherlands

Audio-Language Model Evaluation Speech Processing Automated Evaluation Speech Language Models

Jun 8, 2026cs.SD

Multi-View Speech Representation Learning for Parkinson's Disease Detection Using Context-guided Cross-modal Attention

Parkinson's disease (PD) is a progressive neurodegenerative disorder that frequently causes speech impairments associated with hypokinetic dysarthria. As speech production relies on the precise coordination of complex neuromuscular mechanisms, speech analysis has emerged as a promising non-invasive and cost-effective biomarker for early PD detection. Recent deep learning approaches have shown encouraging results; however, most existing methods rely on a single speech representation, potentially overlooking complementary pathological information encoded across different feature spaces. In this work, we propose a multi-branch deep learning framework for automatic PD detection from speech. Each recording is segmented into 5-second chunks and represented using three complementary modalities: Log-Mel spectrograms, MFCCs, and HuBERT embeddings extracted from raw waveforms. The spectrograms are processed using a pre-trained ResNet-18 encoder, MFCC sequences are modeled through a BiLSTM network, and raw speech is encoded using a pre-trained HuBERT model. To effectively integrate these heterogeneous representations, we introduce a context-guided cross-modal attention mechanism that dynamically weights temporal HuBERT embeddings according to the global acoustic context derived from the spectrogram and MFCC branches. Experiments conducted on the publicly available Spanish PC-GITA corpus under strict speaker-independent 5-fold cross-validation demonstrate the effectiveness of the proposed approach. The proposed architecture achieves an accuracy of 91.51%, an F1-score of 91.24%, and an AUC of 95.97%. Furthermore, ablation studies confirm the contribution of both the proposed context-guided cross-modal attention mechanism and the integration of complementary speech representations. These findings highlight the potential of heterogeneous speech modeling for robust and clinically reliable PD detection.

George Theodosiou, Loukas Ilias, Dimitris Askounis

Decision Support Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, 15780 Athens, Greece

Audio Representation Learning Speech Processing Multimodal Classification Cross-Modal Attention

Jun 8, 2026cs.SD

End-to-End Training for Discrete Token LLM based TTS System

Recent state-of-the-art (SOTA) text-to-speech (TTS) systems typically adopt a cascaded pipeline consisting of a speech tokenizer, an autoregressive large language model (LLM), and a diffusion based flow-matching (FM) model, with these components trained independently. In this paper, we propose a fully end-to-end (E2E) optimization framework that unifies the training of the speech tokenizer, LLM, FM model, and an additional reward model (RM). Specifically, we first jointly optimize the tokenizer using multi-task objectives derived from reconstruction for FM, next-token prediction for LLM, and multi recognition task for RM. This joint training encourages the discrete speech token space to capture acoustically and semantically salient information that is better tailored to TTS. We then further optimize the LLM using downstream reconstruction and recognition by FM and RM, which reduces inference-time mismatch and steers the LLM toward more preferred generations. Experimental results show that our E2E framework consistently outperforms cascaded baselines. On the Seed-TTS-Eval benchmark, our system achieves a word error rate (WER) of 0.78% and 1.56%, a new SOTA result with a 0.6B-parameter LLM and 0.5B-parameter FM model. These results validate that holistic E2E optimization is critical for improving discrete-token-based TTS systems with a much simpler training pipeline.

Changfeng Gao, Yong Ren, Jun Yuan +3

Tencent Yuanbao, China

TTS Synthesis Speech Processing Audio Tokenization Discrete Speech Representation Learning

Jun 8, 2026eess.AS

MeanVC 2: Robust Low-Latency Streaming Zero-Shot Voice Conversion

Streaming zero-shot voice conversion (VC) has become increasingly popular due to its potential for real-time applications. The recently proposed MeanVC achieves lightweight streaming zero-shot VC, but it has several limitations: its chunk-wise autoregressive denoising doubles the effective training sequence length, conversion quality degrades under small-chunk settings, and its timbre encoder directly relies on reference mel-spectrograms, making it sensitive to reference audio quality. To address these limitations we propose MeanVC 2. We introduce future-receptive chunking (FRC), which explicitly schedules past and future receptive fields across diffusion transformer decoder layers and removes clean-chunk teacher forcing. By incorporating bounded future context, FRC enables stable conversion with a 40 ms chunk size. We further introduce a universal timbre token encoder, which constructs a timbre representation from a global speaker embedding and retrieves fine-grained timbre cues via cross-attention, improving robustness to low-quality references and enhancing zero-shot speaker similarity. Experimental results show that MeanVC 2 significantly outperforms MeanVC, while reducing latency from 211 ms to 110 ms. Audio samples are publicly available. The source code will be publicly released.

Guobin Ma, Yuxuan Xia, Yuepeng Jiang +6

The University of New South Wales, Australia · WeNet Open Source Community, China

Diffusion Transformer Audio Diffusion Models Speech Processing Voice Conversion

Jun 7, 2026cs.SD

From A to B to A: Palindromic Zero-Shot Voice Conversion with Non-Parallel Data

We present a voice conversion (VC) framework that utilizes K-Nearest Neighbors (KNN) retrieval over WavLM representations to align non-parallel source and target speech, constructing synthetic training pairs for supervised learning. The retrieved segments serve as synthetic inputs, while real target audio provides ground-truth outputs, forming a synthetic-to-real training paradigm that naturally supports multilingual data without requiring parallel corpora or explicit alignment. To ensure consistent target-speaker identity, we incorporate a speaker loss derived from a pretrained speaker verification model. Experiments across multiple languages demonstrate that the proposed approach achieves high naturalness and strong speaker similarity, outperforming competitive VC baselines, despite being trained exclusively on English data. Samples can be accessed at: https://palindromic-vc.github.io.

Moshe Mandel, Shlomo E. Chazan

Independent, Israel · OriginAI, Israel

Speech Processing Voice Conversion Cross-Lingual Transfer

Jun 7, 2026cs.CL

TRADE: Transducer-Augmented Decoder for Speech LLM

Speech Large Language Models (Speech LLMs) lack a principled mechanism for streaming inference: their label-synchronous generation has no acoustic-frame alignment, making real-time decoding and end-of-utterance detection difficult. We propose TRADE TRansducer-Augmented DEcoder, which augments a multimodal LLM with a transducer branch that shares the audio encoder and uses the LLM's hidden states directly as the prediction network -- coupling frame-synchronous acoustic alignment with the LLM's linguistic reasoning. Three design choices make the system accurate, streamable, and long-form capable: (1)Tightly coupled dual vocabularies -- a compact transducer vocabulary derived from the LLM vocabulary, enabling zero-cost score fusion; (2)Chunk-synchronized streaming training with gradient stopping, eliminating the train-inference mismatch at offline-equivalent memory cost; and (3)Localized Decoder Audio Attention (LDAA), a causal sliding window that caps KV-cache memory independently of utterance length. A single TRADE checkpoint supports offline and streaming decoding across a continuous range of latency operating points. TRADE achieves 6.71% average WER on the Open ASR Leaderboard, while the streaming recognition with 960ms chunk size reaches 8.40% from the same checkpoint. On long-form speech, it obtains 3.64% WER on TED-LIUM and 10.88% on Earnings-22 without external segmentation. TRADE provides sentence-end punctuation timestamps that, when combined with acoustic voice activity detection (VAD), improve end-of-utterance detection by +0.03 F_1 over acoustic VAD alone.

Yun Tang, Shanil Puri, Shinji Watanabe +1

Hippocratic AI · Carnegie Mellon University

Streaming ASR Speech Processing Automatic Speech Recognition Speech Language Models

Jun 6, 2026eess.AS

Paediatric-HGNN: A Hybrid Heterogeneous Graph Neural Network for Detecting Disfluency in Children's Speech via Multiscale Acoustic Fusion

Automated stuttering detection (ASD) systems struggle with paediatric speech due to high acoustic variability in developing voices and the subtle distinction between pathological stuttering and typical developmental disfluencies. We introduce Paediatric-HGNN, a framework using a Context-aware Part-whole Interaction Network (CaPIN) tailored for paediatric data. Instead of conventional 1D signal modelling, our approach builds a heterogeneous graph capturing hierarchical relationships between lexical units (word nodes) and fine-grained acoustic segments (frame nodes). Trained on curated paediatric corpora (UCLASS and FluencyBank), Paediatric-HGNN achieves 82.4% weighted accuracy and a Typical Disfluency F1-score of 0.386. Modelling hierarchical lexical-acoustic interactions captures developmental "searching" behaviour, offering a more robust and interpretable tool for early clinical intervention.

Rashini Liyanarachchi, Rachael Mackay, Alison Short +2

University of New South Wales (UNSW), Sydney, Australia · Resourced Music Therapy, Sydney, Australia · Western Sydney University, Sydney, Australia

Heterogeneous GNNs Speech Processing