10 accepted papers
The INTERSPEECH 2025 Challenge on Multilingual Conversational Speech Language Models (MLC-SLM) promotes multilingual conversational ASR with large language models (LLMs). Our previous SHNU-mASR system adopted a competitive parallel-speech-encoder architecture that integrated Whisper and mHuBERT with…
When there’s a mismatch between the training and test domains, supervised speech enhancement (SE) models trained on synthetic paired noisy-clean data often struggle in real-world scenarios, highlighting the industry’s strong demand for unsupervised training and domain adaptation methods. In this stu…
Many speech enhancement (SE) approaches have been proposed to deal with cocktail party problem. Personalized speech enhancement (PSE) approaches improve SE performance by utilizing user enrollment speech. However, PSE requires users to record additional clean audio for registration, which can be red…
Personalized speech enhancement (PSE) methods typically rely on pre-trained speaker verification models or self-designed speaker encoders to extract target speaker clues, guiding the PSE model in isolating the desired speech. However, these approaches suffer from significant model complexity and oft…
How to effectively use limited supervised accent data to improve the accented ASR is of paramount importance. In this work, we propose an accent-specific quantization for joint unsupervised and supervised training (AQ-JUST) of end-to-end ASR models to address this issue. Specifically, two variants o…
Multi-accent speech recognition is a key challenge in current speech recognition due to the pronunciation variations of different accents. In this study, we propose a Cross-modal Parallel Training (CPT) approach for improving the accent robustness of state-of-the-art Conformer-Transducer (Conformer-…
This paper proposes a new scoring calibration method named "Consistency-Aware Score Calibration", which introduces a Consistency Measure Factor (CMF) to measure the stability of audio voiceprints in similarity scores for speaker verification. The CMF is inspired by the limitations in segment scoring…
In this paper, we propose a new continual learning framework for few-shot bioacoustic event detection (BED). First, we modify the recently proposed dynamic few-shot learning (DFSL) and generalize it to the BED task. Then, we introduce a weight alignment loss to enhance the weight generator of modifi…
In recent years, a number of time-domain speech separation methods have been proposed. However, most of them are very sensitive to the environments and wide domain coverage tasks. In this paper, from the time-frequency domain perspective, we propose a densely-connected pyramid complex convolutional…
The end-to-end approaches for single-channel target speech extraction have attracted widespread attention. However, the studies for end-to-end multi-channel target speech extraction are still relatively limited. In this work, we propose two methods for exploiting the multi-channel spatial informatio…