Related papers: Improving Inference-Time Optimisation for Vocal Ef…
Text-driven style transfer aims to merge the style of a reference image with content described by a text prompt. Recent advancements in text-to-image models have improved the nuance of style transformations, yet significant challenges…
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…
Parameter-efficient transfer learning (PETL) methods have emerged as a solid alternative to the standard full fine-tuning approach. They only train a few extra parameters for each downstream task, without sacrificing performance and…
Accent conversion aims to convert the accent of a source speech to a target accent, meanwhile preserving the speaker's identity. This paper introduces a novel non-autoregressive framework for accent conversion that learns accent-agnostic…
Voice conversion refers to transferring speaker identity with well-preserved content. Better disentanglement of speech representations leads to better voice conversion. Recent studies have found that phonetic information from input audio…
Range estimation of a far field sound source in a reverberant environment is known to be a notoriously difficult problem, hence most localization methods are only capable of estimating the source's Direction-of-Arrival (DoA). In an earlier…
Time-domain training criteria have proven to be very effective for the separation of single-channel non-reverberant speech mixtures. Likewise, mask-based beamforming has shown impressive performance in multi-channel reverberant speech…
In our demo, participants are invited to explore the Diff-MSTC prototype, which integrates the Diff-MST model into Steinberg's digital audio workstation (DAW), Cubase. Diff-MST, a deep learning model for mixing style transfer, forecasts…
Egocentric gaze anticipation serves as a key building block for the emerging capability of Augmented Reality. Notably, gaze behavior is driven by both visual cues and audio signals during daily activities. Motivated by this observation, we…
Current hearing aids normally provide amplification based on a general prescriptive fitting, and the benefits provided by the hearing aids vary among different listening environments despite the inclusion of noise suppression feature.…
Speech data has rich acoustic and paralinguistic information with important cues for understanding a speaker's tone, emotion, and intent, yet traditional large language models such as BERT do not incorporate this information. There has been…
This paper presents a simple yet effective method to achieve prosody transfer from a reference speech signal to synthesized speech. The main idea is to incorporate well-known acoustic correlates of prosody such as pitch and loudness…
Recent strides in the development of diffusion models, exemplified by advancements such as Stable Diffusion, have underscored their remarkable prowess in generating visually compelling images. However, the imperative of achieving a seamless…
Vocal education in the music field is difficult to quantify due to the individual differences in singers' voices and the different quantitative criteria of singing techniques. Deep learning has great potential to be applied in music…
Learning speaker turn embeddings has shown considerable improvement in situations where conventional speaker modeling approaches fail. However, this improvement is relatively limited when compared to the gain observed in face embedding…
Automatic evaluation of ST systems is typically performed by comparing translation hypotheses with one or more reference translations. While effective to some extent, this approach inherits the limitation of reference-based evaluation that…
Deep learning approaches for black-box modelling of audio effects have shown promise, however, the majority of existing work focuses on nonlinear effects with behaviour on relatively short time-scales, such as guitar amplifiers and…
We introduce DiffuseST, a low-latency, direct speech-to-speech translation system capable of preserving the input speaker's voice zero-shot while translating from multiple source languages into English. We experiment with the synthesizer…
Text-to-image (T2I) diffusion models generate high-quality images but often fail to capture the spatial relations specified in text prompts. This limitation can be traced to two factors: lack of fine-grained spatial supervision in training…
Regression prediction plays a crucial role in practical applications and strongly relies on data annotation. However, due to prohibitive annotation costs or domain-specific constraints, labeled data in the target domain is often scarce,…