Pengyuan Zhang

The Conversational Short-phrase Speaker Diarization (CSSD) Task: Dataset, Evaluation Metric and Baselines

2022 · arXiv (Cornell University)

The conversation scenario is one of the most important and most challenging scenarios for speech processing technologies because people in conversation respond to each other in a casual style. Detecting the speech activities of each …

Speech Corpora Divergence Based Unsupervised Data Selection for ASR

2023 · arXiv (Cornell University)

Selecting application scenarios matching data is important for the automatic speech recognition (ASR) training, but it is difficult to measure the matching degree of the training corpus. This study proposes a unsupervised target-aware data selection …

Improving Short Utterance Anti-Spoofing with AASIST2

2023 · arXiv (Cornell University)

The wav2vec 2.0 and integrated spectro-temporal graph attention network (AASIST) based countermeasure achieves great performance in speech anti-spoofing. However, current spoof speech detection systems have fixed training and evaluation durations, while the performance degrades significantly …

Synthetic Speech Detection Based on Temporal Consistency and Distribution of Speaker Features

2023 · arXiv (Cornell University)

Current synthetic speech detection (SSD) methods perform well on certain datasets but still face issues of robustness and interpretability. A possible reason is that these methods do not analyze the deficiencies of synthetic speech. In …

Flexpéro: Flexible Expressive Zero-Shot Speech Refinement via In-Context Learning

2025 · IEEE Signal Processing Letters

Controlling speech expressiveness has emerged as a critical research frontier in speech generation, focusing on synthesizing natural, human-like speech that accurately conveys intended psychological and emotional states. While many large-scale models have demonstrated sufficient zero-shot …