Related papers: Towards Reliable Objective Evaluation Metrics for …
Objective: Speech tests aim to estimate discrimination loss or speech recognition threshold (SRT). This paper investigates the potential to estimate SRTs from clinical data that target at characterizing the discrimination loss. Knowledge…
Pre-trained deep learning embeddings have consistently shown superior performance over handcrafted acoustic features in speech emotion recognition (SER). However, unlike acoustic features with clear physical meaning, these embeddings lack…
Speech separation (SS) has advanced significantly with neural network-based methods, showing improved performance on signal-level metrics. However, these methods often struggle to maintain speech intelligibility in the separated signals,…
Recently, the performance of blind speech separation (BSS) and target speech extraction (TSE) has greatly progressed. Most works, however, focus on relatively well-controlled conditions using, e.g., read speech. The performance may degrade…
Prosody is essential for speech technology, shaping comprehension, naturalness, and expressiveness. However, current text-to-speech (TTS) systems still struggle to accurately capture human-like prosodic variation, in part because existing…
In this paper, we evaluate feature extraction models for predicting speech quality. We also propose a model architecture to compare embeddings of supervised learning and self-supervised learning models with embeddings of speaker…
This paper proposes harmonic vector analysis (HVA) based on a general algorithmic framework of audio blind source separation (BSS) that is also presented in this paper. BSS for a convolutive audio mixture is usually performed by…
Deep noise suppressors (DNS) have become an attractive solution to remove background noise, reverberation, and distortions from speech and are widely used in telephony/voice applications. They are also occasionally prone to introducing…
Ensuring that Text-to-Speech (TTS) systems deliver human-perceived quality at scale is a central challenge for modern speech technologies. Human subjective evaluation protocols such as Mean Opinion Score (MOS) and Side-by-Side (SBS)…
We are interested in a challenging task, Realistic-Music-Score based Singing Voice Synthesis (RMS-SVS). RMS-SVS aims to generate high-quality singing voices given realistic music scores with different note types (grace, slur, rest, etc.).…
Speech deepfake source verification systems aims to determine whether two synthetic speech utterances originate from the same source generator, often assuming that the resulting source embeddings are independent of speaker traits. However,…
Music Structure Analysis (MSA) aims to uncover the high-level organization of musical pieces. State-of-the-art methods are often based on supervised deep learning, but these methods are bottlenecked by the need for heavily annotated data…
Objective metrics for emotional expressiveness are vital for speech generation, particularly in expressive synthesis and voice conversion requiring emotional prosody transfer. To quantify this, the field widely relies on emotion similarity…
In speech generation tasks, human subjective ratings, usually referred to as the opinion score, are considered the "gold standard" for speech quality evaluation, with the mean opinion score (MOS) serving as the primary evaluation metric.…
Speech quality assessment is a critical process in selecting text-to-speech synthesis (TTS) or voice conversion models. Evaluation of voice synthesis can be done using objective metrics or subjective metrics. Although there are many…
Source separation is a crucial pre-processing step for various speech processing tasks, such as automatic speech recognition (ASR). Traditionally, the evaluation metrics for speech separation rely on the matched reference audios and…
We address a blind source separation (BSS) problem in a noisy reverberant environment in which the number of microphones $M$ is greater than the number of sources of interest, and the other noise components can be approximated as stationary…
The ranking of sound event detection (SED) systems may be biased by assumptions inherent to evaluation criteria and to the choice of an operating point. This paper compares conventional event-based and segment-based criteria against the…
The MUSHRA framework is widely used for detecting subtle audio quality differences but traditionally relies on expert listeners in controlled environments, making it costly and impractical for model development. As a result, objective…
Deep neural network based speech enhancement technique focuses on learning a noisy-to-clean transformation supervised by paired training data. However, the task-specific evaluation metric (e.g., PESQ) is usually non-differentiable and can…