相关论文: Continual Speaker Identity Unlearning with Minimal…

Nowadays, as more and more systems achieve good performance in traditional voice conversion (VC) tasks, people's attention gradually turns to VC tasks under extreme conditions. In this paper, we propose a novel method for zero-shot voice…

Recently, large language model (LLM) based text-to-speech (TTS) systems have gradually become the mainstream in the industry due to their high naturalness and powerful zero-shot voice cloning capabilities.Here, we introduce the IndexTTS…

Personalizing a speech synthesis system is a highly desired application, where the system can generate speech with the user's voice with rare enrolled recordings. There are two main approaches to build such a system in recent works: speaker…

We present a meta-learning approach for adaptive text-to-speech (TTS) with few data. During training, we learn a multi-speaker model using a shared conditional WaveNet core and independent learned embeddings for each speaker. The aim of…

Neural codec language models achieve impressive zero-shot Text-to-Speech (TTS) by fully imitating the acoustic characteristics of a short speech prompt, including timbre, prosody, and paralinguistic information. However, such holistic…

We present an unsupervised end-to-end training scheme where we discover discrete subword units from speech without using any labels. The discrete subword units are learned under an ASR-TTS autoencoder reconstruction setting, where an…

On account of growing demands for personalization, the need for a so-called few-shot TTS system that clones speakers with only a few data is emerging. To address this issue, we propose Attentron, a few-shot TTS model that clones voices of…

Unpaired data has shown to be beneficial for low-resource automatic speech recognition~(ASR), which can be involved in the design of hybrid models with multi-task training or language model dependent pre-training. In this work, we leverage…

Current speaker anonymization methods, especially with self-supervised learning (SSL) models, require massive computational resources when hiding speaker identity. This paper proposes an effective and parameter-efficient speaker…

Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities. Previous work addressing privacy issues for language…

Recently, opportunities to transmit speech data to deep learning models executed in the cloud have increased. This has led to growing concerns about speech privacy, including both speaker-specific information and the linguistic content of…

Zero-shot voice conversion (VC) converts source speech into the voice of any desired speaker using only one utterance of the speaker without requiring additional model updates. Typical methods use a speaker representation from a pre-trained…

This paper describes a dataset and protocols for evaluating continuous speech separation algorithms. Most prior studies on speech separation use pre-segmented signals of artificially mixed speech utterances which are mostly \emph{fully}…

Target Speaker Automatic Speech Recognition (TS-ASR) aims to transcribe the speech of a specified target speaker from multi-speaker mixtures in cocktail party scenarios. Recent advancement of Large Audio-Language Models (LALMs) has already…

Deep learning has shown a great potential for speech separation, especially for speech and non-speech separation. However, it encounters permutation problem for multi-speaker separation where both target and interference are speech.…

The inability to filter out in advance all potentially problematic data from the pre-training of large language models has given rise to the need for methods for unlearning specific pieces of knowledge after training. Existing techniques…

One-shot voice conversion (VC) aims to convert speech from any source speaker to an arbitrary target speaker with only a few seconds of reference speech from the target speaker. This relies heavily on disentangling the speaker's identity…

Large Language Models (LLMs) offer extensive knowledge across various domains, but they may inadvertently memorize sensitive, unauthorized, or malicious data, such as personal information in the medical and financial sectors. Machine…

Scaling text-to-speech to a large and wild dataset has been proven to be highly effective in achieving timbre and speech style generalization, particularly in zero-shot TTS. However, previous works usually encode speech into latent using…

For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively…