Related papers: TidyVoice 2026 Challenge Evaluation Plan
In our previous work, we introduced CosyVoice, a multilingual speech synthesis model based on supervised discrete speech tokens. By employing progressive semantic decoding with two popular generative models, language models (LMs) and Flow…
The rapid advances in text-to-speech (TTS) technologies have made audio deepfakes increasingly realistic and accessible, raising significant security and trust concerns. While existing research has largely focused on detecting…
This study aims to develop a single integrated spoofing-aware speaker verification (SASV) embeddings that satisfy two aspects. First, rejecting non-target speakers' input as well as target speakers' spoofed inputs should be addressed.…
This paper introduces FastVC, an end-to-end model for fast Voice Conversion (VC). The proposed model can convert speech of arbitrary length from multiple source speakers to multiple target speakers. FastVC is based on a conditional…
The goal of voice anonymization is to modify an audio such that the true identity of its speaker is hidden. Research on this task is typically limited to the same English read speech datasets, thus the efficacy of current methods for other…
In this paper, we investigate the influence of language similarity in cross-lingual non-target speaker verification trials using a state-of-the-art speaker verification system, ECAPA-TDNN, trained on multilingual and monolingual variants of…
Audio recorded in real-world environments often contains a mixture of foreground speech and background environmental sounds. With rapid advances in text-to-speech, voice conversion, and other generation models, either component can now be…
In automated pronunciation assessment, recent emphasis progressively lies on evaluating multiple aspects to provide enriched feedback. However, acquiring multi-aspect-score labeled data for non-native language learners' speech poses…
We present WiC-TSV, a new multi-domain evaluation benchmark for Word Sense Disambiguation. More specifically, we introduce a framework for Target Sense Verification of Words in Context which grounds its uniqueness in the formulation as a…
Benchmarking plays a pivotal role in assessing and enhancing the performance of compact deep learning models designed for execution on resource-constrained devices, such as microcontrollers. Our study introduces a novel, entirely…
Speech deepfake detection has achieved remarkable success in clean environments but faces significant challenges in complex, real-world scenarios where speech is often mixed with background music or noise. Current state-of-the-art methods…
Speaker segmentation consists in partitioning a conversation between one or more speakers into speaker turns. Usually addressed as the late combination of three sub-tasks (voice activity detection, speaker change detection, and overlapped…
The ICASSP 2021 Acoustic Echo Cancellation Challenge is intended to stimulate research in the area of acoustic echo cancellation (AEC), which is an important part of speech enhancement and still a top issue in audio communication and…
Speaker verification systems often degrade significantly when there is a language mismatch between training and testing data. Being able to improve cross-lingual speaker verification system using unlabeled data can greatly increase the…
The mechanism proposed here is for real-time speaker change detection in conversations, which firstly trains a neural network text-independent speaker classifier using in-domain speaker data. Through the network, features of conversational…
In this paper, we present X-Voice, a 0.4B multilingual zero-shot voice cloning model that clones arbitrary voices and enables everyone to speak 30 languages. X-Voice is trained on a 420K-hour multilingual corpus using the International…
Cross-modal associations between voice and face from a person can be learnt algorithmically, which can benefit a lot of applications. The problem can be defined as voice-face matching and retrieval tasks. Much research attention has been…
An utterance-level speaker embedding is typically obtained by aggregating a sequence of frame-level representations. However, in real-world scenarios, individual frames encode not only speaker-relevant information but also various nuisance…
Cross-lingual dubbing of lecture videos requires the transcription of the original audio, correction and removal of disfluencies, domain term discovery, text-to-text translation into the target language, chunking of text using target…
Large language models (LLMs) are increasingly integral as productivity assistants, but existing benchmarks fall short in rigorously evaluating their real-world instruction-following capabilities. Current benchmarks often (i) lack sufficient…