Related papers: DNN No-Reference PSTN Speech Quality Prediction

Many recently published Text-to-Speech (TTS) systems produce audio close to real speech. However, TTS evaluation needs to be revisited to make sense of the results obtained with the new architectures, approaches and datasets. We propose…

Self-attention mechanisms have enabled transformers to achieve superhuman-level performance on many speech-to-text (STT) tasks, yet the challenge of automatic prosodic segmentation has remained unsolved. In this paper we finetune Whisper, a…

Speech enhancement concerns the processes required to remove unwanted background sounds from the target speech to improve its quality and intelligibility. In this paper, a novel approach for single-channel speech enhancement is presented,…

Personalized speech enhancement (PSE) models can improve the audio quality of teleconferencing systems by adapting to the characteristics of a speaker's voice. However, most existing methods require a separate speaker embedding model to…

Facial recognition system is one of the major successes of Artificial intelligence and has been used a lot over the last years. But, images are not the only biometric present: audio is another possible biometric that can be used as an…

Voice-over-Internet-Protocol (VoIP) calls are prone to various speech impairments due to environmental and network conditions resulting in bad user experience. A reliable audio impairment classifier helps to identify the cause for bad audio…

The calculation of most objective speech intelligibility assessment metrics requires clean speech as a reference. Such a requirement may limit the applicability of these metrics in real-world scenarios. To overcome this limitation, we…

Within the area of speech enhancement, there is an ongoing interest in the creation of neural systems which explicitly aim to improve the perceptual quality of the processed audio. In concert with this is the topic of non-intrusive (i.e.…

Non-intrusive speech quality assessment (SQA) systems suffer from limited training data and costly human annotations, hindering their generalization to real-time conferencing calls. In this work, we propose leveraging large language models…

Developing robust speaker verification (SV) systems without speaker labels has been a longstanding challenge. Earlier research has highlighted a considerable performance gap between self-supervised and fully supervised approaches. In this…

We present a textless speech-to-speech translation (S2ST) system that can translate speech from one language into another language and can be built without the need of any text data. Different from existing work in the literature, we tackle…

Recent speech synthesis systems based on sampling from autoregressive neural networks models can generate speech almost undistinguishable from human recordings. However, these models require large amounts of data. This paper shows that the…

The potential of synthetic data in text-to-speech (TTS) model training has gained increasing attention, yet its rationality and effectiveness require systematic validation. In this study, we systematically investigate the feasibility of…

Packet loss concealment (PLC) is a tool for enhancing speech degradation caused by poor network conditions or underflow/overflow in audio processing pipelines. We propose a real-time recurrent method that leverages previous outputs to…

Human judgments obtained through Mean Opinion Scores (MOS) are the most reliable way to assess the quality of speech signals. However, several recent attempts to automatically estimate MOS using deep learning approaches lack robustness and…

Zero-shot Text-To-Speech (TTS) synthesis shows great promise for personalized voice customization through voice cloning. However, current methods for achieving zero-shot TTS heavily rely on large model scales and extensive training datasets…

End-to-end speech-to-speech translation (S2ST) without relying on intermediate text representations is a rapidly emerging frontier of research. Recent works have demonstrated that the performance of such direct S2ST systems is approaching…

During the compression, transmission, and rendering of point clouds, various artifacts are introduced, affecting the quality perceived by the end user. However, evaluating the impact of these distortions on the overall quality is a…

Deep neural network (DNN)-based speech enhancement usually uses a clean speech as a training target. However, it is hard to collect large amounts of clean speech because the recording is very costly. In other words, the performance of…

While supervised quality predictors for synthesized speech have demonstrated strong correlations with human ratings, their requirement for in-domain labeled training data hinders their generalization ability to new domains. Unsupervised…