Speech & Audio - Weekly Roundup

Multi-round active simulation turns standard neural density estimators into high-precision, test-time-specialized solvers for notoriously ill-posed physical inverse problems.

SSL-based audio deepfake detectors consistently fail on out-of-distribution attacks because static layer aggregation blinds them to localized spoofing artifacts—a vulnerability resolved here through dynamic, sample-adaptive layer gating and multi-granularity feature fusion.

Contemporary frontier speech models still catastrophically fail on living Arabic dialects, with top systems like GPT-4o achieving an error rate no better than 35.0% WER across 17 regional vernaculars.

Standard speech metrics fail to capture how code-switching transcription errors cascade into critical task failures in production enterprise voice agents.

Conversational 3D heads no longer need static weights: turning live dyadic audiovisual streams into an online self-supervised training signal makes avatar motion up to 11.1% more coherent as dialogues unfold.

Multi-round active simulation turns standard neural density estimators into high-precision, test-time-specialized solvers for notoriously ill-posed physical inverse problems.

SSL-based audio deepfake detectors consistently fail on out-of-distribution attacks because static layer aggregation blinds them to localized spoofing artifacts—a vulnerability resolved here through dynamic, sample-adaptive layer gating and multi-granularity feature fusion.

Contemporary frontier speech models still catastrophically fail on living Arabic dialects, with top systems like GPT-4o achieving an error rate no better than 35.0% WER across 17 regional vernaculars.

Standard speech metrics fail to capture how code-switching transcription errors cascade into critical task failures in production enterprise voice agents.

Conversational 3D heads no longer need static weights: turning live dyadic audiovisual streams into an online self-supervised training signal makes avatar motion up to 11.1% more coherent as dialogues unfold.

Control accent strength in zero-shot TTS with a single model and inference-time weight, outperforming cascaded systems on out-of-domain accents without sacrificing speaker identity.

Timbre drift in multi-turn expressive voice agents can be eliminated by replacing implicit context embeddings with explicitly supervised style instructions optimized via rejection sampling and context-aware DPO.

TFA is introduced, a reliability-guided, training-free aggregation method requiring neither place labels nor task-specific weight updates that can recover additional retrieval capability from frozen representations, providing a practical baseline for new environments with scarce place supervision.

It is concluded that cross-paper ASR comparison is currently unsupported, and a ten-item reporting checklist targeted at each failure is proposed, to supply the shared measurement contract the field has so far done without.

StreamTN is proposed, a lightweight LLM-based Chinese streaming TN model that employs a dual-track streaming framework in which input tokens and output tokens are processed on two parallel tracks, enabling low-latency real-time inference without complex prompting.

This work training a LALM with reinforcement learning to reason over its own speech output generates a draft speech as a form of audio-token reasoning, critiques its own generation by reflecting on the acoustic realization in text, and produces a refined version conditioned on both the first-pass speech and the critique.

This work proposes replacing an empty representation with a learnable unconditional embedding, optimized to represent a meaningful unconditional state, and shows that learnable null embeddings consistently outperform fixed null embeddings across speaker similarity, speech stability, and expressiveness, while exhibiting greater robustness to larger guidance scales.

This work proposes an end-to-end text-to-speech model that augments the text encoding mechanism with a morpho-syntactic prior and replaces the standard phoneme encoder in the VITS architecture with a morpheme sequence encoder and a phoneme-to-morpheme attention network.

AURA is proposed, an ultra-efficient representation-editing method that freezes the pretrained model and applies sparse scale-and-shift edits to decoder cross-attention heads, supporting dynamic activation editing as a practical path for grounding AED speech models.