Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.16858

What Makes Codec Tokens Effective for Target Speaker Extraction? A Semantic-Acoustic Disentanglement Perspective

Wang Xiang·Bang Zeng·Ming Li
View original source ↗Read source document ↗Export metadata ↓

Abstract

Target speaker extraction (TSE) aims to recover a target speaker's speech from a speech mixture using an enrollment utterance. Recent codec-based generative approaches formulate TSE as conditional speech token generation and achieve promising perceptual quality. However, most existing systems rely on unified codec tokens that entangle linguistic content, speaker characteristics, and acoustic details, forcing a single model to jointly handle target selection, content semantic, and acoustic reconstruction. In this paper, we investigate whether disentangled semantic-acoustic codec representations are better suited to TSE. We first show that simply replacing unified codec tokens with semantic-acoustic tokens is insufficient and can even degrade performance when both remain handled by a unified generative model. Motivated by this observation, we propose a task-aware discriminative-generative framework, where a discriminative branch extracts target-related semantic information, while a generative branch predicts coarse acoustic tokens and refines them under semantic guidance. This specialization separates what is said from how it sounds while coordinating both factors in a factorized codec space. Experiments on Libri2Mix show that our method reduces dWER from 0.388 to 0.118 compared with a unified-codec baseline, while maintaining competitive perceptual quality and speaker consistency. Ablation studies confirm that the gains arise from task-aware semantic-acoustic modeling rather than representation disentanglement alone.

Explore related subjects

cs.SD

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Wang Xiang, Bang Zeng, Ming Li. 2026-10-12. What Makes Codec Tokens Effective for Target Speaker Extraction? A Semantic-Acoustic Disentanglement Perspective. https://arxiv.org/abs/2610.16858

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Loud-loss: A Perceptually Motivated Loss Function for Speech Enhancement Based on Equal-Loudness Contours

The mean squared error (MSE) is a ubiquitous loss function for speech enhancement, but its problem is that the error cannot reflect the auditory perception quality. This is because MSE causes models to over-emphasize low-frequency components which has high energy, leading to the inadequate modeling of perceptually important high-frequency information. To overcome this limitation, we propose a perceptually-weighted loss function grounded in psychoacoustic principles. Specifically, it leverages equal-loudness contours to assign frequency-dependent weights to the reconstruction error, thereby penalizing deviations in a way aligning with human auditory sensitivity. The proposed loss is model-agnostic and flexible, demonstrating strong generality. Experiments on the VoiceBank+DEMAND dataset show that replacing MSE with our loss in a GTCRN model elevates the WB-PESQ score from 2.17 to 2.93-a significant improvement in perceptual quality.

cs.SD↗
arXiv2026

Auto-AEG: Scalable Data Construction for Open-Vocabulary Audio Event Grounding

Large Audio-Language Models (LALMs) reason fluently about sound yet struggle to localize precisely when events occur, while classical Sound Event Detection (SED) attains frame-level precision only over a closed label set. At the intersection of these paradigms lies the task of Open-Vocabulary Audio Event Grounding: predicting all time intervals of a target sound event described by an arbitrary natural language query. Progress is bottlenecked by data scarcity: no large-scale resource provides open-vocabulary onset/offset supervision, and manual temporal annotation is prohibitively expensive. To address this, we introduce Auto-AEG, a scalable pipeline that constructs such supervision by automatic data construction and model fine-tuning. It pairs programmatically synthesized clips, which carry placement-exact ground-truth intervals for supervised cold-start, with multi-model pseudo-labels on real-world audio that supply the reward signal for reinforcement learning. Training with this pipeline yields large temporal-localization gains on AEGBench, an independent difficulty-stratified benchmark whose annotations we release, and these gains generalize to various held-out SED and audio grounding benchmarks. Our results show that automatically constructed data, coupled with interval-aware reward design, provides an effective data-side route to expanding the temporal localization capability of LALMs.

cs.SD↗
arXiv2026

TontaubeV1: Streaming Text-to-Speech with Hierarchical Codec Modeling and Bounded Context

Text-to-speech systems often face a trade-off between natural prosody and efficient inference: higher perceptual quality usually comes at increased computational cost and latency. We present TontaubeV1, a model that preserves natural prosody while enabling streaming from a single consumer GPU. Speech is encoded by the hierarchical DualCodec representation at 12.5 Hz, which separates a semantic stream from successive acoustic refinements. Our design assumes that prosodic structure is largely established when the semantic stream is generated, and allocates capacity accordingly: a Qwen3-1.7B-derived transformer predicts that stream and thereby the utterance duration, while three progressively smaller Qwen3-0.6B-derived transformers each add one acoustic refinement. Text is tokenized per character rather than by subword. Paired text and audio markers at shared positions support long-form generation with bounded context, and overlapping DualCodec reconstructions are mapped into the VibeVoice acoustic latent space and decoded causally, enabling streaming despite DualCodec's noncausal decoder. The model accepts up to one minute of reference audio for voice conditioning and is designed primarily for English and German, with additional multilingual support. The four predictors total 2.9B parameters; on a single RTX 5090 the streaming path reaches about 200 ms to first audio. In separate non-streaming measurements, the end-to-end real-time factor (RTF) is 0.08 for one input and the aggregate RTF is 0.02 across eight concurrent inputs. In a blinded study, 40 listeners preferred TontaubeV1's prosody over Fish Audio S2 Pro in 70.25% of 400 comparisons (95% CI: 64.2-75.7%). On an LLM-as-a-judge benchmark, it matches ElevenLabs Flash v2.5 and outperforms the April 2026 Gradium API and Cartesia Sonic 3 on prosody. The weights are released on Hugging Face under the Tontaube Community Model License 1.0.

cs.SD↗