相关论文: SHEET: A Multi-purpose Open-source Speech Human Ev…

We participated in track 2 of the VoiceMOS Challenge 2024, which aimed to predict the mean opinion score (MOS) of singing samples. Our submission secured the first place among all participating teams, excluding the official baseline. In…

This research introduces an enhanced version of the multi-objective speech assessment model--MOSA-Net+, by leveraging the acoustic features from Whisper, a large-scaled weakly supervised model. We first investigate the effectiveness of…

Perceptually-inspired objective functions such as the perceptual evaluation of speech quality (PESQ), signal-to-distortion ratio (SDR), and short-time objective intelligibility (STOI), have recently been used to optimize performance of…

The IEEE Spoken Language Technology Workshop (SLT) 2021 Alpha-mini Speech Challenge (ASC) is intended to improve research on keyword spotting (KWS) and sound source location (SSL) on humanoid robots. Many publications report significant…

The objective speech quality assessment is usually conducted by comparing received speech signal with its clean reference, while human beings are capable of evaluating the speech quality without any reference, such as in the mean opinion…

The goal of multilingual speech technology is to facilitate seamless communication between individuals speaking different languages, creating the experience as though everyone were a multilingual speaker. To create this experience, speech…

Speech quality estimation has recently undergone a paradigm shift from human-hearing expert designs to machine-learning models. However, current models rely mainly on supervised learning, which is time-consuming and expensive for label…

Advancements in audio foundation models (FMs) have fueled interest in end-to-end (E2E) spoken dialogue systems, but different web interfaces for each system makes it challenging to compare and contrast them effectively. Motivated by this,…

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…

Self-supervised learning (SSL) speech models, which can serve as powerful upstream models to extract meaningful speech representations, have achieved unprecedented success in speech representation learning. However, their effectiveness on…

In this study, we propose a cross-domain multi-objective speech assessment model called MOSA-Net, which can estimate multiple speech assessment metrics simultaneously. Experimental results show that MOSA-Net can improve the linear…

There is a growing interest in cost-effective self-supervised fine-tuning (SSFT) of self-supervised learning (SSL)-based speech models to obtain task-specific representations. These task-specific representations are used for robust…

Acoustic scene classification (ASC) predominantly relies on supervised approaches. However, acquiring labeled data for training ASC models is often costly and time-consuming. Recently, self-supervised learning (SSL) has emerged as a…

Spoken question answering (SQA) systems are critical for digital assistants and other real-world use cases, but evaluating their performance is a challenge due to the importance of human-spoken questions. This study presents a new…

In spoken question answering, the systems are designed to answer questions from contiguous text spans within the related speech transcripts. However, the most natural way that human seek or test their knowledge is via human conversations.…

In this paper, we present an update to the NISQA speech quality prediction model that is focused on distortions that occur in communication networks. In contrast to the previous version, the model is trained end-to-end and the…

The INTERSPEECH 2020 Deep Noise Suppression Challenge is intended to promote collaborative research in real-time single-channel Speech Enhancement aimed to maximize the subjective (perceptual) quality of the enhanced speech. A typical…

While various end-to-end models for spoken language understanding tasks have been explored recently, this paper is probably the first known attempt to challenge the very difficult task of end-to-end spoken question answering (SQA). Learning…

Self-supervised learning (SSL) has helped extend speech technologies to more languages by reducing the need for labeled data. However, models are still far from supporting the world's 7000+ languages. We propose XEUS, a Cross-lingual…

Automatic subjective speech quality assessment (SSQA) traditionally estimates speech quality on an utterance or system level. While this resolution was adequate for older transmission or synthesis systems that produced speech signals of…