17 papers
How Reliable Are Predicted MOS for Reproducing Human System-Level Preferences in Speech Enhancement?
Nahomi Kusunoki, Tsubasa Ochiai, Naohiro Tawara +4
We investigate whether predicted Mean Opinion Scores (MOS) can reliably support system-level comparisons of speech enhancement (SE) methods by introducing system-level preference a…
Diarization Error Decomposition Under Pause Annotation Ambiguity
Shota Horiguchi, Marc Delcroix, Naohiro Tawara +1
Speaker diarization evaluation is sensitive to ambiguity in pause annotation, which can inflate diarization error rate (DER) or obscure genuine model errors. We show that morpholog…
Over-Tightening-Aware Pseudo-Labeling for Tight-Boundary Speaker Diarization
Shota Horiguchi, Takanori Ashihara, Marc Delcroix +2
Training speaker diarization models on loose labels, such as speech segments with padded boundaries or filled pauses, often results in similarly loose model outputs. To obtain tigh…
Ontology-based Target Sound Extraction
Carlos Hernandez-Olivan, Marc Delcroix, Tsubasa Ochiai +2
Target sound extraction (TSE) aims to isolate a sound source of interest from a mixture, given a semantic query. Existing TSE systems are conditioned on fixed class representations…
M3-DuplexBench: A Multi-Turn, Multilingual, Multidomain Benchmark for Full-Duplex Spoken Dialogue Models
Ryo Fukuda, Atsushi Ando, Hiroki Kanagawa +4
Full-duplex spoken dialogue systems (FDSDSs) can listen while speaking, enabling natural conversational behaviors such as smooth turn-taking, backchannel handling, and user barge-i…
SLT 2026 REAL-TSE Challenge: Real-world Target Speaker Extraction from Conversational Recordings
Shuai Wang, Zihan Qian, Ke Zhang +9
We introduce the REAL-TSE Challenge, an IEEE SLT 2026 satellite challenge on target speaker extraction~(TSE) from real conversational recordings. Given a multi-speaker mixture and…
SphereVBx: Spherical Variational Bayes Clustering for Simplified EEND-VC Diarization
Petr Pálka, Jiangyu Han, Prachi Singh +3
We propose SphereVBx, a Bayesian clustering framework for hyperspherical embeddings based on Toroidal Probabilistic Spherical Discriminant Analysis (T-PSDA). The method follows the…
Evaluating Large Language Models Abilities for Addressee, Turn-change, and Next Speaker Prediction in Meetings
Ryo Fukuda, Takatomo Kano, Siddhant Arora +7
We investigate turn-taking in multimodal multi-party conversations using large language models (LLMs). We construct an evaluation framework for three tasks: addressee detection, tu…
Non-Autoregressive Minimum Bayes' Risk Decoding for Fast Speech Recognition
Hiroyuki Deguchi, Takatomo Kano, Katsuki Chousa +1
Non-autoregressive (NAR) decoding generates output tokens in parallel, making speech recognition faster than autoregressive decoding, which generates them sequentially from left to…
Generating Training Targets for Real-World Speech Enhancement via Close-to-Distant Microphone Projection
Tomohiro Nakatani, Rintaro Ikeshita, Naoyuki Kamo +2
Training neural networks (NNs) for speech enhancement (SE) in distant speech-capturing scenarios requires paired distorted and clean reference speech signals. While such data are o…
Tight Boundary Prediction in Speaker Diarization Using Causal-Anticausal Consistency
Shota Horiguchi, Marc Delcroix, Naohiro Tawara +2
Multi-talker conversational automatic speech recognition data are often used to train speaker diarization models. Because such data prioritize semantic continuity, pauses and bound…
Description and Discussion on DCASE 2026 Challenge Task 4: Spatial Semantic Segmentation of Sound Scenes
Binh Thien Nguyen, Masahiro Yasuda, Noboru Harada +8
This paper presents an overview of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2026 Challenge Task 4, Spatial Semantic Segmentation of Sound Scenes (S5).…
Who Spoke What When? Evaluating Spoken Language Models for Conversational ASR with Semantic and Overlap-Aware Metrics
Naohiro Tawara, Samuele Cornell, Alexander Polok +3
Conversational automatic speech recognition remains challenging due to overlapping speech, far-field noise, and varying speaker counts. While recent LLM-based systems perform well…
FlexIO: Flexible Single- and Multi-Channel Speech Separation and Enhancement
Yoshiki Masuyama, Kohei Saijo, Francesco Paissan +6
Speech separation and enhancement (SSE) has advanced remarkably and achieved promising results in controlled settings, such as a fixed number of speakers and a fixed array configur…
VBx for End-to-End Neural and Clustering-based Diarization
Petr Pálka, Jiangyu Han, Marc Delcroix +2
We present improvements to speaker diarization in the two-stage end-to-end neural diarization with vector clustering (EEND-VC) framework. The first stage employs a Conformer-based…
Spatially Aware Self-Supervised Models for Multi-Channel Neural Speaker Diarization
Jiangyu Han, Ruoyu Wang, Yoshiki Masuyama +4
Self-supervised models such as WavLM have demonstrated strong performance for neural speaker diarization. However, these models are typically pre-trained on single-channel recordin…
Efficient and Robust Speaker Diarization via Structured Pruning of Self-Supervised Models
Jiangyu Han, Petr Pálka, Marc Delcroix +4
This work presents a framework for compressing self-supervised models for speaker diarization through structured pruning guided by knowledge distillation. We investigate pruning ob…