Related papers: Low-frequency Compensated Synthetic Impulse Respon…

The rhythm of bonafide speech is often difficult to replicate, which causes that the fundamental frequency (F0) of synthetic speech is significantly different from that of real speech. It is expected that the F0 feature contains the…

The awareness for biased ASR datasets or models has increased notably in recent years. Even for English, despite a vast amount of available training data, systems perform worse for non-native speakers. In this work, we improve an…

In this work, we propose a full-band real-time speech enhancement system with GAN-based stochastic regeneration. Predictive models focus on estimating the mean of the target distribution, whereas generative models aim to learn the full…

Speech synthesis models convert written text into natural-sounding audio. While earlier models were limited to a single speaker, recent advancements have led to the development of zero-shot systems that generate realistic speech from a wide…

Recent success of the Tacotron speech synthesis architecture and its variants in producing natural sounding multi-speaker synthesized speech has raised the exciting possibility of replacing expensive, manually transcribed, domain-specific,…

This paper proposes a dual-stage, low complexity, and reconfigurable technique to enhance the speech contaminated by various types of noise sources. Driven by input data and audio contents, the proposed dual-stage speech enhancement…

Self-supervised learning of speech representations has achieved impressive results in improving automatic speech recognition (ASR). In this paper, we show that data selection is important for self-supervised learning. We propose a simple…

Synthesized speech is common today due to the prevalence of virtual assistants, easy-to-use tools for generating and modifying speech signals, and remote work practices. Synthesized speech can also be used for nefarious purposes, including…

The rapid advancement of generative models has enabled highly realistic audio deepfakes, yet current detectors suffer from a critical bias problem, leading to poor generalization across unseen datasets. This paper proposes Artifact-Focused…

Pseudo-relevance feedback (PRF) is a classical approach to address lexical mismatch by enriching the query using first-pass retrieval. Moreover, recent work on generative-relevance feedback (GRF) shows that query expansion models using text…

In this paper, we perform an in-depth study of how data augmentation techniques improve synthetic or spoofed audio detection. Specifically, we propose methods to deal with channel variability, different audio compressions, different…

We present FastPitch, a fully-parallel text-to-speech model based on FastSpeech, conditioned on fundamental frequency contours. The model predicts pitch contours during inference. By altering these predictions, the generated speech can be…

Speech enhancement is a critical component of many user-oriented audio applications, yet current systems still suffer from distorted and unnatural outputs. While generative models have shown strong potential in speech synthesis, they are…

Logical Access (LA) attacks, also known as audio deepfake attacks, use Text-to-Speech (TTS) or Voice Conversion (VC) methods to generate spoofed speech data. This can represent a serious threat to Automatic Speaker Verification (ASV)…

Neurodivergent people frequently experience decreased sound tolerance, with estimates suggesting it affects 50-70% of this population. This heightened sensitivity can provoke reactions ranging from mild discomfort to severe distress,…

We propose a multi-stage framework for universal speech enhancement, designed for the Interspeech 2025 URGENT Challenge. Our system first employs a Sparse Compression Network to robustly separate sources and extract an initial clean speech…

Acquiring training data to improve the robustness of dialog systems can be a painstakingly long process. In this work, we propose a method to reduce the cost and effort of creating new conversational agents by artificially generating more…

Expressive text-to-speech systems have undergone significant advancements owing to prosody modeling, but conventional methods can still be improved. Traditional approaches have relied on the autoregressive method to predict the quantized…

In visual Reinforcement Learning (RL), upstream representation learning largely determines the effect of downstream policy learning. Employing auxiliary tasks allows the agent to enhance visual representation in a targeted manner, thereby…

Transformers, originally proposed for natural language processing (NLP) tasks, have recently achieved great success in automatic speech recognition (ASR). However, adjacent acoustic units (i.e., frames) are highly correlated, and…