Related papers: A framework of text-dependent speaker verification…

Training a text-to-speech (TTS) model requires a large scale text labeled speech corpus, which is troublesome to collect. In this paper, we propose a transfer learning framework for TTS that utilizes a large amount of unlabeled speech…

Trained on 680,000 hours of massive speech data, Whisper is a multitasking, multilingual speech foundation model demonstrating superior performance in automatic speech recognition, translation, and language identification. However, its…

Target speaker extraction (TSE) relies on a reference cue of the target to extract the target speech from a speech mixture. While a speaker embedding is commonly used as the reference cue, such embedding pre-trained with a large number of…

Target-Speaker Voice Activity Detection (TS-VAD) utilizes a set of speaker profiles alongside an input audio signal to perform speaker diarization. While its superiority over conventional methods has been demonstrated, the method can suffer…

Recent advances in unsupervised speech representation learning discover new approaches and provide new state-of-the-art for diverse types of speech processing tasks. This paper presents an investigation of using wav2vec 2.0 deep speech…

Text-to-Speech (TTS) models have advanced significantly, aiming to accurately replicate human speech's diversity, including unique speaker identities and linguistic nuances. Despite these advancements, achieving an optimal balance between…

Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis. However, effectively mapping the complex, multidimensional attributes of speech into discrete tokens remains…

Deep neural network approaches to speaker verification have proven successful, but typical computational requirements of State-Of-The-Art (SOTA) systems make them unsuited for embedded applications. In this work, we present a two-stage…

With the continuous development of speech recognition technology, speaker verification (SV) has become an important method for identity authentication. Traditional SV methods rely on handcrafted feature extraction, while deep learning has…

Although high-fidelity speech can be obtained for intralingual speech synthesis, cross-lingual text-to-speech (CTTS) is still far from satisfactory as it is difficult to accurately retain the speaker timbres(i.e. speaker similarity) and…

Multi-taper estimators provide low-variance power spectrum estimates that can be used in place of the windowed discrete Fourier transform (DFT) to extract speech features such as mel-frequency cepstral coefficients (MFCCs). Even if past…

Deep speaker embedding extractors have already become new state-of-the-art systems in the speaker verification field. However, the problem of verification score calibration for such systems often remains out of focus. An irrelevant score…

Spoofing-robust automatic speaker verification (SASV) systems are a crucial technology for the protection against spoofed speech. In this study, we focus on logical access attacks and introduce a novel approach to SASV tasks. A novel…

There are a number of studies about extraction of bottleneck (BN) features from deep neural networks (DNNs)trained to discriminate speakers, pass-phrases and triphone states for improving the performance of text-dependent speaker…

Multilingual speaker verification (SV) remains challenging due to limited cross-lingual data and language-dependent information in speaker embeddings. This paper presents a language-invariant multilingual SV system for the TidyVoice 2026…

This paper presents the T02 team's system for the Singing Voice Conversion Challenge 2023 (SVCC2023). Our system entails a VITS-based SVC model, incorporating three modules: a feature extractor, a voice converter, and a post-processor.…

Recent advancements in speech synthesis witness significant benefits by leveraging discrete tokens extracted from self-supervised learning (SSL) models. Discrete tokens offer higher storage efficiency and greater operability in intermediate…

Despite the rapid progress of automatic speech recognition (ASR) technologies targeting normal speech in recent decades, accurate recognition of dysarthric and elderly speech remains highly challenging tasks to date. Sources of…

Self-supervised speech models learn representations that capture both content and speaker information. Yet this entanglement creates problems: content tasks suffer from speaker bias, and privacy concerns arise when speaker identity leaks…

For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker…