相关论文: End-to-end streaming model for low-latency speech …

We propose DarkStream, a streaming speech synthesis model for real-time speaker anonymization. To improve content encoding under strict latency constraints, DarkStream combines a causal waveform encoder, a short lookahead buffer, and…

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…

Streaming voice conversion has become increasingly popular for its potential in real-time applications. The recently proposed DualVC 2 has achieved robust and high-quality streaming voice conversion with a latency of about 180ms.…

Speaker anonymization aims to conceal a speaker's identity without degrading speech quality and intelligibility. Most speaker anonymization systems disentangle the speaker representation from the original speech and achieve anonymization by…

This paper presents an end-to-end text-to-speech system with low latency on a CPU, suitable for real-time applications. The system is composed of an autoregressive attention-based sequence-to-sequence acoustic model and the LPCNet vocoder…

In recent years, developing a speech understanding system that classifies a waveform to structured data, such as intents and slots, without first transcribing the speech to text has emerged as an interesting research problem. This work…

Transformer-based models have achieved state-of-the-art performance on speech translation tasks. However, the model architecture is not efficient enough for streaming scenarios since self-attention is computed over an entire input sequence…

Speaker anonymization aims to protect the privacy of speakers while preserving spoken linguistic information from speech. Current mainstream neural network speaker anonymization systems are complicated, containing an F0 extractor, speaker…

Attention-based models have been gaining popularity recently for their strong performance demonstrated in fields such as machine translation and automatic speech recognition. One major challenge of attention-based models is the need of…

In recent years, the need for privacy preservation when manipulating or storing personal data, including speech , has become a major issue. In this paper, we present a system addressing the speaker-level anonymization problem. We propose…

The social media revolution has produced a plethora of web services to which users can easily upload and share multimedia documents. Despite the popularity and convenience of such services, the sharing of such inherently personal data,…

Protecting speaker identity is crucial for online voice applications, yet streaming speaker anonymization (SA) remains underexplored. Recent research has demonstrated that neural audio codec (NAC) provides superior speaker feature…

Cascaded speech-to-speech translation systems often suffer from the error accumulation problem and high latency, which is a result of cascaded modules whose inference delays accumulate. In this paper, we propose a transducer-based speech…

The attention-based Transformer model has achieved promising results for speech recognition (SR) in the offline mode. However, in the streaming mode, the Transformer model usually incurs significant latency to maintain its recognition…

This work proposes a frame-wise online/streaming end-to-end neural diarization (EEND) method, which detects speaker activities in a frame-in-frame-out fashion. The proposed model mainly consists of a causal embedding encoder and an online…

An inferior performance of the streaming automatic speech recognition models versus non-streaming model is frequently seen due to the absence of future context. In order to improve the performance of the streaming model and reduce the…

The development of privacy-preserving automatic speaker verification systems has been the focus of a number of studies with the intent of allowing users to authenticate themselves without risking the privacy of their voice. However, current…

Speech 'in-the-wild' is a handicap for speaker recognition systems due to the variability induced by real-life conditions, such as environmental noise and the emotional state of the speaker. Taking advantage of the principles of…

Voice anonymization has been developed as a technique for preserving privacy by replacing the speaker's voice in a speech signal with that of a pseudo-speaker, thereby obscuring the original voice attributes from machine recognition and…

Achieving super-human performance in recognizing human speech has been a goal for several decades, as researchers have worked on increasingly challenging tasks. In the 1990's it was discovered, that conversational speech between two humans…