Audio and Speech Processing Papers of the Week

We propose Continual Residual Memory (CRM), a gradient-free continual TTA framework for selective residual recovery.

In particular, how models acquire editing capabilities and the relationship between generation and editing remain unclear. To address these challenges, we introduce VoxCanvas-41M, a large-scale bilingual dataset comprising approximately 41 million speech editing pairs.

We propose a unified multi-encoder framework that supports both invasive and non-invasive modeling for robust lyric intelligibility prediction.

However, CLAP is limited in capturing fine-grained musical attributes such as timbre and expressiveness \emph{etc}. To address this, we propose FUSEMOS, a dual-encoder fusion framework that integrates CLAP with MERT, a self-supervised model pretrained on large scale music audio, to better capture both high level semantic alignment and detailed musical characteristics for more accurate OMI and TA estimation.

We present Spatial Transfusion, a unified first-order ambisonics (FOA) framework that extends a pretrained spatial audio understanding model to generation and editing through flow matching over VAE latents.

We evaluate three audiocapable models on acted, conversational and spontaneous speech (eNTERFACE'05, MELD and CMU-MOSEI).

We present GSLM2, which learns and models complementary properties of speech at multiple levels of abstraction.

In this paper, we introduce SPHERE (Spatial and Perceptual Human Evaluation and Rating Estimator), a multidimensional no-reference perceptual evaluation framework for binaural speech.

We propose Cross-Layer Relation Modeling (\ours{}), which explicitly encodes cross-layer relations alongside layer-specific features, making both directly available for ADD.

However, grounding such a generative TSE model with speaker-confused evidence may therefore reinforce the error. To address this gap, we proposed a repair-before-grounding framework with a training-free evidence-repair stage.

This paper introduces Pop Goes the Verifier, a stealthier phoneme injection poisoning attack.

In this work, we introduce Grounded Generative Speech Recognition (GSR), reformulating speech recognition as generating semantically grounded text instead of a single transcript.

Here, we propose training latent diffusion/flow-based music generation models conditioned on structured captions (SCAPs) and compare with typical free-form captions via a set of controlled ablations.

Predictive processing and sensory adaptation suggest retaining predictable input locally and responding selectively to deviations. Inspired by this mechanism, we propose Predictive Signed-Dyadic Coding (PG).

This study proposes and evaluates a Human–AI Collaborative Blended Learning Framework for the development of English as a Foreign Language (EFL) speaking skills.

Transcribing the recording first makes it fit but discards sounds and voices, while systems that return to the audio must be trained for this behavior. We propose ReListen, a training-free method in which a frozen audio language model finds its own evidence before answering.

In this work, we investigate TASU-style posterior alignment as a means of mitigating paired-data scarcity in multilingual ASR.

In this work, we propose SPATEX, the first array-flexible MIMO TSE framework that reconstructs microphone-wise target speech signals across microphone counts and array geometries.

This paper investigates the effectiveness of parameter-efficient fine-tuning (PEFT) for adapting pretrained music encoders and examines whether modality-specific improvements translate into better multimodal representations.