MAPSS: Manifold-based Assessment of Perceptual Source Separation

Objective assessment of source-separation systems still mismatches subjective human perception, especially when leakage and self-distortion interact. We introduce the Perceptual Separation (PS) and Perceptual Match (PM), the first pair of measures that functionally isolate these two factors. Our intrusive method begins with generating a bank of fundamental distortions for each reference waveform signal in the mixture. Distortions, references, and their respective system outputs from all sources are then independently encoded by a pre-trained self-supervised learning model. These representations are aggregated and projected onto a manifold via diffusion maps, which aligns Euclidean distances on the manifold with dissimilarities of the encoded waveforms. On this manifold, the PM measures the Mahalanobis distance from each output to its attributed cluster that consists of its reference and distortions embeddings, capturing self-distortion. The PS accounts for the Mahalanobis distance of the output to the attributed and to the closest non-attributed clusters, quantifying leakage. Both measures are differentiable and granular, operating at a resolution as low as 50 frames per second. We further derive, for both measures, deterministic error radius and non-asymptotic, high-probability confidence intervals (CIs). Experiments on English, Spanish, and music mixtures show that the PS and PM nearly always achieve the highest linear correlation coefficients with human mean-opinion scores than 14 competitors, reaching as high as 86.36% for speech and 87.21% for music. We observe, at worst, an error radius of 1.39% and a probabilistic 95% CI of 12.21% for these coefficients, which improves reliable and informed evaluation. Using mutual information, the measures complement each other most as their values decrease, suggesting they are jointly more informative as system performance degrades.

HISPASpoof: A New Dataset For Spanish Speech Forensics

Zero-shot Voice Cloning (VC) and Text-to-Speech (TTS) methods have advanced rapidly, enabling the generation of highly realistic synthetic speech and raising serious concerns about their misuse. While numerous detectors have been developed for English and Chinese, Spanish-spoken by over 600 million people worldwide-remains underrepresented in speech forensics. To address this gap, we introduce HISPASpoof, the first large-scale Spanish dataset designed for synthetic speech detection and attribution. It includes real speech from public corpora across six accents and synthetic speech generated with six zero-shot TTS systems. We evaluate five representative methods, showing that detectors trained on English fail to generalize to Spanish, while training on HISPASpoof substantially improves detection. We also evaluate synthetic speech attribution performance on HISPASpoof, i.e., identifying the generation method of synthetic speech. HISPASpoof thus provides a critical benchmark for advancing reliable and inclusive speech forensics in Spanish.

Deploying AI for Signal Processing education: Selected challenges and intriguing opportunities

Powerful artificial intelligence (AI) tools that have emerged in recent years -- including large language models, automated coding assistants, and advanced image and speech generation technologies -- are the result of monumental human achievements. These breakthroughs reflect mastery across multiple technical disciplines and the resolution of significant technological challenges. However, some of the most profound challenges may still lie ahead. These challenges are not purely technical but pertain to the fair and responsible use of AI in ways that genuinely improve the global human condition. This article explores one promising application aligned with that vision: the use of AI tools to facilitate and enhance education, with a specific focus on signal processing (SP). It presents two interrelated perspectives: identifying and addressing technical limitations, and applying AI tools in practice to improve educational experiences. Primers are provided on several core technical issues that arise when using AI in educational settings, including how to ensure fairness and inclusivity, handle hallucinated outputs, and achieve efficient use of resources. These and other considerations -- such as transparency, explainability, and trustworthiness -- are illustrated through the development of an immersive, structured, and reliable "smart textbook." The article serves as a resource for researchers and educators seeking to advance AI's role in engineering education.

TextlessRAG: End-to-End Visual Document RAG by Speech Without Text

Document images encapsulate a wealth of knowledge, while the portability of spoken queries enables broader and flexible application scenarios. Yet, no prior work has explored knowledge base question answering over visual document images with queries provided directly in speech. We propose TextlessRAG, the first end-to-end framework for speech-based question answering over large-scale document images. Unlike prior methods, TextlessRAG eliminates ASR, TTS and OCR, directly interpreting speech, retrieving relevant visual knowledge, and generating answers in a fully textless pipeline. To further boost performance, we integrate a layout-aware reranking mechanism to refine retrieval. Experiments demonstrate substantial improvements in both efficiency and accuracy. To advance research in this direction, we also release the first bilingual speech--document RAG dataset, featuring Chinese and English voice queries paired with multimodal document content. Both the dataset and our pipeline will be made available at repository:https://github.com/xiepeijinhit-hue/textlessrag

Machine Learning-Based Prediction of Speech Arrest During Direct Cortical Stimulation Mapping

Identifying cortical regions critical for speech is essential for safe brain surgery in or near language areas. While Electrical Stimulation Mapping (ESM) remains the clinical gold standard, it is invasive and time-consuming. To address this, we analyzed intracranial electrocorticographic (ECoG) data from 16 participants performing speech tasks and developed machine learning models to directly predict if the brain region underneath each ECoG electrode is critical. Ground truth labels indicating speech arrest were derived independently from Electrical Stimulation Mapping (ESM) and used to train classification models. Our framework integrates neural activity signals, anatomical region labels, and functional connectivity features to capture both local activity and network-level dynamics. We found that models combining region and connectivity features matched the performance of the full feature set, and outperformed models using either type alone. To classify each electrode, trial-level predictions were aggregated using an MLP applied to histogram-encoded scores. Our best-performing model, a trial-level RBF-kernel Support Vector Machine together with MLP-based aggregation, achieved strong accuracy on held-out participants (ROC-AUC: 0.87, PR-AUC: 0.57). These findings highlight the value of combining spatial and network information with non-linear modeling to improve functional mapping in presurgical evaluation.

Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling

We introduce Delayed Streams Modeling (DSM), a flexible formulation for streaming, multimodal sequence-to-sequence learning. Sequence-to-sequence generation is often cast in an offline manner, where the model consumes the complete input sequence before generating the first output timestep. Alternatively, streaming sequence-to-sequence rely on learning a policy for choosing when to advance on the input stream, or write to the output stream. DSM instead models already time-aligned streams with a decoder-only language model. By moving the alignment to a pre-processing step,and introducing appropriate delays between streams, DSM provides streaming inference of arbitrary output sequences, from any input combination, making it applicable to many sequence-to-sequence problems. In particular, given text and audio streams, automatic speech recognition (ASR) corresponds to the text stream being delayed, while the opposite gives a text-to-speech (TTS) model. We perform extensive experiments for these two major sequence-to-sequence tasks, showing that DSM provides state-of-the-art performance and latency while supporting arbitrary long sequences, being even competitive with offline baselines. Code, samples and demos are available at https://github.com/kyutai-labs/delayed-streams-modeling

Joint Learning using Mixture-of-Expert-Based Representation for Enhanced Speech Generation and Robust Emotion Recognition

Speech emotion recognition (SER) plays a critical role in building emotion-aware speech systems, but its performance degrades significantly under noisy conditions. Although speech enhancement (SE) can improve robustness, it often introduces artifacts that obscure emotional cues and adds computational overhead to the pipeline. Multi-task learning (MTL) offers an alternative by jointly optimizing SE and SER tasks. However, conventional shared-backbone models frequently suffer from gradient interference and representational conflicts between tasks. To address these challenges, we propose the Sparse Mixture-of-Experts Representation Integration Technique (Sparse MERIT), a flexible MTL framework that applies frame-wise expert routing over self-supervised speech representations. Sparse MERIT incorporates task-specific gating networks that dynamically select from a shared pool of experts for each frame, enabling parameter-efficient and task-adaptive representation learning. Experiments on the MSP-Podcast corpus show that Sparse MERIT consistently outperforms baseline models on both SER and SE tasks. Under the most challenging condition of -5 dB signal-to-noise ratio (SNR), Sparse MERIT improves SER F1-macro by an average of 12.0% over a baseline relying on a SE pre-processing strategy, and by 3.4% over a naive MTL baseline, with statistical significance on unseen noise conditions. For SE, Sparse MERIT improves segmental SNR (SSNR) by 28.2% over the SE pre-processing baseline and by 20.0% over the naive MTL baseline. These results demonstrate that Sparse MERIT provides robust and generalizable performance for both emotion recognition and enhancement tasks in noisy environments.

LatentVoiceGrad: Nonparallel Voice Conversion with Latent Diffusion/Flow-Matching Models

Previously, we introduced VoiceGrad, a nonparallel voice conversion (VC) technique enabling mel-spectrogram conversion from source to target speakers using a score-based diffusion model. The concept involves training a score network to predict the gradient of the log density of mel-spectrograms from various speakers. VC is executed by iteratively adjusting an input mel-spectrogram until resembling the target speaker's. However, challenges persist: audio quality needs improvement, and conversion is slower compared to modern VC methods designed to operate at very high speeds. To address these, we introduce latent diffusion models into VoiceGrad, proposing an improved version with reverse diffusion in the autoencoder bottleneck. Additionally, we propose using a flow matching model as an alternative to the diffusion model to further speed up the conversion process without compromising the conversion quality. Experimental results show enhanced speech quality and accelerated conversion compared to the original.

Accelerating Diffusion Transformer-Based Text-to-Speech with Transformer Layer Caching

This paper presents a method to accelerate the inference process of diffusion transformer (DiT)-based text-to-speech (TTS) models by applying a selective caching mechanism to transformer layers. Specifically, I integrate SmoothCache into the F5-TTS architecture, focusing on caching outputs of self-attention and feed-forward network layers to reduce redundant computations during the denoising process. A calibration phase is introduced to analyze L1 relative errors between timesteps, guiding the selection of cache schedules that minimize quality degradation. To address the problem of inter-layer dependency, a unified caching schedule is adopted, applying the cache pattern derived from self-attention layers to both layer types. Experiments on LibriSpeech-PC and Seed-TTS datasets evaluate various cache thresholds and denoising step configurations. Results show that caching at higher denoising steps reduces inference time without compromising output quality, whereas caching at lower steps can negatively impact synthesis quality similarly to reducing the total number of denoising steps. Objective and subjective metrics confirm the effectiveness of SmoothCache in maintaining performance while improving computational efficiency. Comparisons between cached inference and reduced-step inference further highlight the benefits of selective caching, especially under high-step configurations. This work demonstrates that transformer layer caching is a practical solution for optimizing diffusion transformer-based TTS models without requiring architectural changes or retraining. Example inference results can be heard at https://siratish.github.io/F5-TTS_SmoothCache/ .

CommonVoice-SpeechRE and RPG-MoGe: Advancing Speech Relation Extraction with a New Dataset and Multi-Order Generative Framework

Speech Relation Extraction (SpeechRE) aims to extract relation triplets directly from speech. However, existing benchmark datasets rely heavily on synthetic data, lacking sufficient quantity and diversity of real human speech. Moreover, existing models also suffer from rigid single-order generation templates and weak semantic alignment, substantially limiting their performance. To address these challenges, we introduce CommonVoice-SpeechRE, a large-scale dataset comprising nearly 20,000 real-human speech samples from diverse speakers, establishing a new benchmark for SpeechRE research. Furthermore, we propose the Relation Prompt-Guided Multi-Order Generative Ensemble (RPG-MoGe), a novel framework that features: (1) a multi-order triplet generation ensemble strategy, leveraging data diversity through diverse element orders during both training and inference, and (2) CNN-based latent relation prediction heads that generate explicit relation prompts to guide cross-modal alignment and accurate triplet generation. Experiments show our approach outperforms state-of-the-art methods, providing both a benchmark dataset and an effective solution for real-world SpeechRE. The source code and dataset are publicly available at https://github.com/NingJinzhong/SpeechRE_RPG_MoGe.