Related papers: Evaluating Objective Speech Quality Metrics for Ne…
The recent advancement of end-to-end neural audio codecs enables compressing audio at very low bitrates while reconstructing the output audio with high fidelity. Nonetheless, such improvements often come at the cost of increased model…
Neural audio codecs (NACs) have made significant advancements in recent years and are rapidly being adopted in many audio processing pipelines. However, they can introduce audio distortions which degrade speaker verification (SV)…
Wideband codecs such as AMR-WB or EVS are widely used in (mobile) speech communication. Evaluation of coded speech quality is often performed subjectively by an absolute category rating (ACR) listening test. However, the ACR test is…
State-of-the-art spoken dialogue models (D\'efossez et al. 2024; Schalkwyk et al. 2025) use neural audio codecs to "tokenize" audio signals into a lower-frequency stream of vectorial latent representations, each quantized using a hierarchy…
Research into the prediction and analysis of perceived audio quality is hampered by the scarcity of openly available datasets of audio signals accompanied by corresponding subjective quality scores. To address this problem, we present the…
Machine learning techniques are an active area of research for speech enhancement for hearing aids, with one particular focus on improving the intelligibility of a noisy speech signal. Recent work has shown that feature encodings from…
Natural and artificial audition can in principle acquire different solutions to a given problem. The constraints of the task, however, can nudge the cognitive science and engineering of audition to qualitatively converge, suggesting that a…
ITU-R BS.1387 states a method for objective assessment of perceived audio quality. This Recommendation, known also as PEAQ (Perceptual Evaluation of Audio Quality) is based on a psychoacoustic model of the human ear and was standardized by…
Although recent neural text-to-speech (TTS) systems have achieved high-quality speech synthesis, there are cases where a TTS system generates low-quality speech, mainly caused by limited training data or information loss during knowledge…
Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modeling techniques to audio data. However, audio codecs often…
A good audio codec for live applications such as telecommunication is characterized by three key properties: (1) compression, i.e.\ the bitrate that is required to transmit the signal should be as low as possible; (2) latency, i.e.\…
We present BigCodec, a low-bitrate neural speech codec. While recent neural speech codecs have shown impressive progress, their performance significantly deteriorates at low bitrates (around 1 kbps). Although a low bitrate inherently…
It has been shown recently that deep learning based models are effective on speech quality prediction and could outperform traditional metrics in various perspectives. Although network models have potential to be a surrogate for complex…
Recent work in the domain of speech enhancement has explored the use of self-supervised speech representations to aid in the training of neural speech enhancement models. However, much of this work focuses on using the deepest or final…
Existing objective evaluation metrics for voice conversion (VC) are not always correlated with human perception. Therefore, training VC models with such criteria may not effectively improve naturalness and similarity of converted speech. In…
The quantification of audio aesthetics remains a complex challenge in audio processing, primarily due to its subjective nature, which is influenced by human perception and cultural context. Traditional methods often depend on human…
Despite rapid advancements in TTS models, a consistent and robust human evaluation framework is still lacking. For example, MOS tests fail to differentiate between similar models, and CMOS's pairwise comparisons are time-intensive. The…
The diverse perceptual consequences of hearing loss severely impede speech communication, but standard clinical audiometry, which is focused on threshold-based frequency sensitivity, does not adequately capture deficits in frequency and…
With neural video codecs (NVCs) emerging as promising alternatives for traditional compression methods, it is increasingly important to determine whether existing quality metrics remain valid for evaluating their performance. However, few…
This paper proposes an approach to improve Non-Intrusive speech quality assessment(NI-SQA) based on the residuals between impaired speech and enhanced speech. The difficulty in our task is particularly lack of information, for which the…