Neural Speech Tracking in a Virtual Acoustic Environment: Audio-Visual Benefit for Unscripted Continuous Speech

Mareike Daeglau; Juergen Otten; Giso Grimm; Bojana Mirkovic; Volker Hohmann; Stefan Debener

Home/Archive/arXiv

arXiv · 2501.08124

Neural Speech Tracking in a Virtual Acoustic Environment: Audio-Visual Benefit for Unscripted Continuous Speech

Mareike Daeglau·Juergen Otten·Giso Grimm·Bojana Mirkovic·Volker Hohmann·Stefan Debener

View original source ↗Read source document ↗Export metadata ↓

Abstract

The audio visual benefit in speech perception, where congruent visual input enhances auditory processing, is well documented across age groups, particularly in challenging listening conditions and among individuals with varying hearing abilities. However, most studies rely on highly controlled laboratory environments with scripted stimuli. Here, we examine the audio visual benefit using unscripted, natural speech from untrained speakers within a virtual acoustic environment. Using electroencephalography (EEG) and cortical speech tracking, we assessed neural responses across audio visual, audio only, visual only, and masked lip conditions to isolate the role of lip movements. Additionally, we analysed individual differences in acoustic and visual features of the speakers, including pitch, jitter, and lip openness, to explore their influence on the audio visual speech tracking benefit. Results showed a significant audio visual enhancement in speech tracking with background noise, with the masked lip condition performing similarly to the audio-only condition, emphasizing the importance of lip movements in adverse listening situations. Our findings reveal the feasibility of cortical speech tracking with naturalistic stimuli and underscore the impact of individual speaker characteristics on audio-visual integration in real world listening contexts.

Explore related subjects

eess.AS cs.SD

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Mareike Daeglau, Juergen Otten, Giso Grimm, Bojana Mirkovic, Volker Hohmann, Stefan Debener. 2025-01-14. Neural Speech Tracking in a Virtual Acoustic Environment: Audio-Visual Benefit for Unscripted Continuous Speech. https://arxiv.org/abs/2501.08124

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

KEEP EXPLORING

Related papers

arXiv2026

Recovering the Zipfian Distribution in Unsupervised Term Discovery

Unsupervised term discovery involves segmenting unlabelled speech into word- or syllable-like units and clustering these into a lexicon of candidate types. True lexicons follow a Zipfian distribution, yet the dominant centre-based clustering approach -- K-means -- produces a more uniform distribution due to an inductive bias toward spherical clusters. In this paper we revisit graph-based clustering as a bottom-up alternative, where segment embeddings are connected by pairwise similarity and partitioned using the Leiden algorithm. We show that graph clustering substantially outperforms centre-based approaches (K-means, GMM, BIRCH) in both word- and syllable-level lexicon discovery across three languages, producing more Zipf-like distributions. Another bottom-up approach, agglomerative clustering with average linkage, also performs well, although it is computationally less efficient and allows for less control over the resulting distribution. Our work calls into question the dominance of centre-based clustering for term discovery, and promotes graph clustering as an attractive alternative.

eess.AS↗

arXiv2026

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation

Strong speech-to-text (S2T) LLMs already provide robust speech perception and text reasoning, but adding speech-to-speech (S2S) output is challenging: fine-tuning the backbone can degrade the original S2T performance, while attaching a downstream talker reintroduces a serial text-to-speech bottleneck. We present PRIME-Speech, a frozen-backbone S2S conversion framework that trains only speech-generation modules. PRIME-Speech synchronizes a causal audio post-decoder with intermediate hidden states of the frozen backbone, so codec tokens are generated from the model's evolving reasoning trajectory rather than from completed text chunks. The post-decoder uses mixed hidden-state, text, and audio-history conditioning, and a training-time packing strategy with turn-level audio KV-cache and position reset stabilizes multi-turn spoken interaction without additional multi-turn S2S training data. Multi-token prediction further reduces the effective codec prediction rate and improves first-audio latency without modifying the reasoning path. Across speech translation, spoken QA, speech understanding, and multi-turn dialogue, PRIME-Speech preserves the S2T behavior of the frozen backbone while producing accurate, low-WER spoken responses.

eess.AS↗

arXiv2026

Brain2Speech-Net: Fast and Intelligible Brain-to-Speech Synthesis Without Text Decoding

The loss of speech limits communication for individuals with paralysis. Direct neural-to-speech synthesis is challenging due to the limited availability of neural data for training speech brain-computer interfaces. Most existing systems rely on cascaded neural-to-text-to-speech pipelines, which increase inference latency and propagate errors across stages. We present Brain2Speech-Net, a single-stage neural-to-speech generation framework without intermediate text decoding. We use a differentiable phoneme bottleneck and a deep-HMM alignment mechanism to map long neural recordings into the latent space of a text-to-speech (TTS) model, enabling high-quality speech synthesis. Brain2Speech-Net is the only system in our comparison that produces intelligible speech while generating faster than real time.

eess.AS↗